Data processing method and device and electronic equipment

Abstract

The invention discloses a data processing method and device and electronic equipment. The method comprises the steps of obtaining loan service data of a target enterprise and employee transaction data and enterprise transaction data in a plurality of transaction scenes in response to a monitoring request for a loan service of the target enterprise; dividing the employee transaction data, the enterprise transaction data and the loan business data into a plurality of data sets based on the transaction identifiers of the employee transaction data and the enterprise transaction data, the loan identifier of the loan business data and the association relationship between the transaction identifiers and the loan identifier and a preset index, each data set comprises at least one piece of transaction data or at least one piece of loan business data, and each data set corresponds to a preset index; determining an index value of each preset index based on the transaction data and / or loan business data in each data set; and managing and controlling the target enterprise based on the index value of each preset index. Through the method, the accuracy and efficiency of post-loan management can be improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a data processing method, device and electronic device. Background Art

[0002] Credit business is one of the main financial businesses of financial institutions. Post-loan management of credit business is from the occurrence of credit business to the collection of principal and interest. In the existing technology, credit account managers generally conduct irregular visits to enterprises that have been granted loans to understand the business conditions, financial conditions and use of loan funds. At the same time, the use of credit business is monitored to ensure that the loan funds are used for the agreed purpose. In the post-loan management process, if it is found that the customer has a risk of default or other situations that may affect the safety of the loan, the credit account manager needs to take necessary measures in a timely manner, such as adjusting the loan amount, recovering the loan in advance, etc., to prevent, control and resolve business risks.

[0003] At present, traditional post-loan management methods mainly rely on manual work, which requires a lot of human resources, and manual management often cannot guarantee work efficiency and accuracy. In addition, the data involved in traditional post-loan management are usually scattered in different departments or systems, which makes data integration and sharing difficult, affecting the accuracy of risk assessment and repayment monitoring. Traditional post-loan management relies on manual inspection and internal information systems, and the level of intelligence is relatively low, resulting in deficiencies in risk identification, early warning and collection, and it is difficult to cope with the increasingly complex financial market environment. It can be seen that the existing technology has low reliability in monitoring credit business and low timeliness in data processing.

[0004] Currently, no effective solution has been proposed to the above-mentioned problem of being unable to monitor credit business quickly and accurately. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a data processing method, device and electronic device to solve the problem of being unable to quickly and accurately monitor credit business.

[0006] In order to solve the above technical problems, the first aspect of this specification provides a data processing method, including:

[0007] In response to a monitoring request for a target enterprise's loan business, obtaining the target enterprise's loan business data and employee transaction data and enterprise transaction data under multiple transaction scenarios, where different transaction scenarios correspond to different transaction identifiers;

[0008] Based on the transaction identifiers of the employee transaction data and the enterprise transaction data, the loan identifier of the loan business data, and the association between the transaction identifier and the loan identifier and the preset indicator, the employee transaction data, the enterprise transaction data, and the loan business data are divided into a plurality of data sets, each of which includes at least one transaction data or at least one loan business data, and each of which corresponds to a preset indicator;

[0009] Determine the indicator value of each preset indicator based on the transaction data and / or loan business data in each data set;

[0010] Based on the indicator values ​​of each preset indicator, the loan business is managed and controlled.

[0011] In some embodiments of this specification, obtaining the target enterprise's loan business data and employee transaction data and enterprise transaction data in multiple transaction scenarios includes:

[0012] Collecting real-time transaction log data from a target terminal and a target application in real time, and performing structured processing on the real-time transaction log data to obtain the employee transaction data;

[0013] Based on the fee payment transaction identifier, the wage payment transaction identifier, the loan identifier and the preset period, the fee payment business data, the wage payment business data and the loan business data of the target enterprise are collected in batches, wherein the fee payment business data and the wage payment business data are the enterprise transaction data.

[0014] In some embodiments of this specification, the real-time transaction log data is structured to obtain the employee transaction data, including:

[0015] Establishing a data connection relationship between the real-time transaction log data and the employee transaction data, and a data transmission relationship between the real-time transaction log data of the target terminal and the real-time transaction log data of the target application;

[0016] Based on the data transmission relationship, data fusion is performed on the real-time transaction log data of the target terminal and the real-time transaction log data of the target application to obtain fused transaction log data;

[0017] Based on the data connection relationship, stream computing is performed on the fused transaction log data to obtain the employee transaction data.

[0018] In some embodiments of this specification, the real-time transaction log data is structured to obtain the employee transaction data, including:

[0019] Use Kafka to build a real-time data channel between real-time transaction log data and employee transaction data;

[0020] Using Sqoop to establish a data transmission relationship between the real-time transaction log data of the target terminal and the real-time transaction log data of the target application;

[0021] Based on the real-time data channel and the transmission relationship, a stream computing model is constructed using Storm;

[0022] The real-time transaction log data is processed using a stream computing model to obtain the employee transaction data.

[0023] In some embodiments of the present specification, based on the agency fee payment transaction identifier, agency wage payment transaction identifier, loan identifier and preset period, batch collection of agency fee payment business data, agency wage payment business data and loan business data of the target enterprise includes:

[0024] Constructing enterprise transaction data clusters, and constructing data coordination nodes corresponding to the agency payment business, agency salary payment business, and loan business respectively, and associating the constructed data coordination nodes with the agency payment transaction identifier, agency salary payment transaction identifier, and loan identifier respectively;

[0025] The data coordination node is used to batch collect business data associated with the corresponding data coordination node from the enterprise transaction data cluster according to a preset period, and the collected business data is structured to obtain the payment agency business data, the salary agency business data and the loan business data.

[0026] In some embodiments of the present specification, based on the transaction data and / or loan business data in each data set, determining the indicator value of each preset indicator includes:

[0027] Determine the transaction elements corresponding to each transaction data and / or the business elements corresponding to the loan business data in the data set;

[0028] Based on the mapping relationship between the indicator value of the preset indicator corresponding to the data set and the transaction elements and / or business elements, and the element value of each transaction element and / or business element, the indicator value of the preset indicator corresponding to the data set is determined.

[0029] In some embodiments of this specification, the loan business is managed and controlled based on the indicator values ​​of each preset indicator, including:

[0030] Determine the risk level of the target enterprise based on the indicator value of each preset indicator and the mapping relationship between the risk level and the indicator range of each preset indicator;

[0031] The loan business is managed and controlled accordingly based on the risk level of the target enterprise.

[0032] In some embodiments of this specification, the loan business is managed and controlled based on the indicator values ​​of each preset indicator, including:

[0033] Calculating the risk score of the target enterprise based on the indicator value of each preset indicator and the weight corresponding to each preset indicator, wherein the weight corresponding to each preset indicator is determined by the indicator data of the historical loan business;

[0034] Determine the risk level of the target enterprise based on the risk score of the target enterprise and the mapping relationship between each risk level and the risk score range;

[0035] The loan business is managed and controlled accordingly based on the risk level of the target enterprise.

[0036] A second aspect of the present specification provides a data processing device, including:

[0037] A data acquisition module, for responding to a monitoring request for a target enterprise's loan business, acquiring the target enterprise's loan business data and employee transaction data and enterprise transaction data under multiple transaction scenarios, where different transaction scenarios correspond to different transaction identifiers;

[0038] a data partitioning module, configured to partition the employee transaction data, the enterprise transaction data, and the loan business data into a plurality of data sets based on the transaction identifiers of the employee transaction data and the enterprise transaction data, the loan identifiers of the loan business data, and the association between the transaction identifiers and the loan identifiers and the preset indicators, each data set including at least one transaction data or at least one loan business data, and each data set corresponding to a preset indicator;

[0039] A data processing module, used to determine the index value of each preset index based on the transaction data and / or loan business data in each data set;

[0040] The control module is used to control the loan business based on the indicator values ​​of each preset indicator.

[0041] A third aspect of the present specification provides an electronic device, including:

[0042] A memory and a processor, wherein the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the steps of the method described in the first aspect.

[0043] A fourth aspect of the present specification provides a computer storage medium, wherein the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the steps of the method described in the first aspect are implemented.

[0044] A fifth aspect of the present specification provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0045] The data processing method in the embodiments of this specification can directly collect employee transaction data and enterprise transaction data, as well as loan business data, which represent the daily life flow of the target enterprise and its employees, from the system database without relying on external data sources. Therefore, when a loan business monitoring request from the target enterprise is received, data can be quickly acquired, and an accurate and reliable data basis can be provided for the calculation of the index values ​​of each preset index. Moreover, the employee transaction data and enterprise transaction data can correspond to multiple levels of transaction information in multiple transaction scenarios. When calculating the index value, the acquired data of multiple transaction scenarios are integrated, and the acquired data are divided into multiple data sets based on the correlation between each transaction scenario and each preset index. Based on the data in each data set, the target enterprise is evaluated from the dimensions corresponding to each preset index, and multiple index values ​​for a more comprehensive and detailed characterization of the target enterprise are obtained, thereby improving the accuracy and efficiency of post-loan management of the loan business. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some implementation methods recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0047] Figure 1 Shown is a schematic diagram of a data processing method provided by an embodiment of this specification;

[0048] Figure 2 Shown is a schematic diagram of a data processing method provided by an embodiment of this specification;

[0049] Figure 3 FIG. 1 is a schematic diagram of a data processing device provided in an embodiment of the present specification;

[0050] Figure 4 Shown is a schematic diagram of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0052] It should be noted that the user-related information and data involved in the embodiments of this specification are all information and data authorized by the user or fully authorized by relevant parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users or relevant parties to choose to authorize or refuse.

[0053] It should also be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0054] Credit risk control refers to the identification, assessment, monitoring and control of risks in credit business by financial institutions through a series of management measures and strategies in credit business, so as to maintain a balance between risk and benefit, ensure the safety of funds and improve the quality of credit assets. The core of credit risk management lies in predicting and managing risks. There are corresponding risk control and management actions in the three links of pre-loan, loan and post-loan, and risks need to be quantified through key data information.

[0055] In terms of data acquisition for post-loan management, financial institutions generally construct post-loan management early warning models through industrial and commercial registration information data, corporate and legal person credit data, corporate account repayment record data, corporate order data, corporate equity relationship data, corporate legal person and shareholder guarantee data, etc. Industrial and commercial registration information data, corporate and legal person credit data, corporate equity relationship data, corporate legal person and shareholder guarantee data are all data collected by non-financial institution systems and are third-party data.

[0056] Among them, the industrial and commercial registration information data is collected and maintained by the industrial and commercial administrative departments. Although it can reflect the registration status and basic information of the enterprise, its update frequency and accuracy may be affected by various factors. For example, there may be a lag in the change of enterprise information, and the level of industrial and commercial administration in different regions is different, and the integrity and consistency of the data are difficult to guarantee. The credit data of enterprises and legal persons are usually collected by credit reporting agencies, which collect credit information of enterprises and individuals through various channels. However, the collection channels and methods of these data vary, and there may be problems such as insufficient data coverage and untimely data updates, which in turn affect its accuracy and timeliness. In addition, the data sources of credit reporting agencies may be biased, and some information may not fully reflect the credit status of enterprises or legal persons.

[0057] The data on corporate equity relations involves the shareholder composition and equity structure of the enterprise, which is mainly derived from industrial and commercial registration and self-reported data of enterprises. In some cases, such data may be concealed or falsely reported, especially in enterprises with complex shareholder relationships or conflicts of interest. This further increases the risk of data accuracy. Similar problems exist in the data on corporate legal persons and shareholder guarantees. These data are usually collected by enterprises through self-reporting or third-party agencies, and it is difficult to ensure their comprehensiveness and authenticity. Some enterprises or individuals may fail to truthfully report guarantee information for various reasons, resulting in reduced data reliability.

[0058] It can be seen that although third-party data can provide some data support for the post-loan management of enterprises, there are uncertainties in the accuracy and timeliness of the data. The cost for financial institutions to obtain enterprise order data is high, and there is also a high threshold for verifying the authenticity of the data.

[0059] In addition, although enterprise order data, as a data that directly reflects the business conditions of enterprises, is of great value to financial institutions in assessing corporate credit, the cost of obtaining it is high. Financial institutions need to invest a lot of resources in data collection and verification, especially since the order data of small and medium-sized enterprises is scattered and opaque, which further increases the difficulty of verifying the authenticity of the data. And due to the confidentiality of enterprise order data, financial institutions have great difficulties in obtaining and verifying data.

[0060] In order to solve the above problems, an embodiment of the present specification provides a data processing method, which obtains the loan business data of the target enterprise and the employee transaction data and enterprise transaction data in multiple transaction scenarios in response to a monitoring request for the loan business of the target enterprise, and different transaction scenarios correspond to different transaction identifiers; based on the transaction identifiers of the employee transaction data and the enterprise transaction data, the loan identifier of the loan business data, and the association between the transaction identifier and the loan identifier and the preset indicator, the employee transaction data, the enterprise transaction data and the loan business data are divided into multiple data sets, each data set includes at least one transaction data or at least one loan business data, and each data set corresponds to a preset indicator; based on the transaction data and / or loan business data in each data set, the indicator value of each preset indicator is determined; based on the indicator value of each preset indicator, the target enterprise is managed and controlled.

[0061] In the embodiments of this specification, employee transaction data and enterprise transaction data, as well as loan business data, which characterize the daily life flow of the target enterprise and its employees, can be directly collected from the system database without relying on external data sources, thereby providing an accurate and reliable data basis for the calculation of the index values ​​of each preset index; moreover, the employee transaction data and enterprise transaction data can correspond to multiple levels of transaction information in multiple transaction scenarios. When calculating the index value, the data of multiple transaction scenarios obtained are integrated, and the target enterprise is evaluated from the dimensions corresponding to each preset indicator in combination with the correlation between each transaction scenario and each preset indicator, so as to obtain multiple indicator values ​​for a more comprehensive and detailed characterization of the target enterprise, thereby improving the accuracy and efficiency of post-loan management of the loan business.

[0062] It can be understood that the above method provided in the present application can be applied to electronic devices, and electronic devices can refer to electronic devices with data calculation, processing and storage capabilities. The electronic device can be a terminal such as a PC (Personal Computer), a tablet computer, a smart phone, a wearable device, an intelligent robot, etc.; it can also be a server. Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0063] The data processing method provided in the embodiment of the present application is introduced below in conjunction with the accompanying drawings.

[0064] Figure 1Shown is a schematic diagram of the data processing method provided by the embodiment of this specification. Although this specification provides method operation steps or device structures as shown in the following embodiments or drawings, the method or device may include more or fewer operation steps or module units after partial merger based on routine or no creative labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or drawings of this specification. When the method or module structure is applied in actual devices, servers or terminal products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or drawings (for example, in an environment of parallel processors or multi-threaded processing, or even including distributed processing, server cluster implementation environment). As Figure 1 As shown, the method may include steps S101 to S104, specifically:

[0065] S101: In response to a monitoring request for a target enterprise's loan business, obtain the target enterprise's loan business data and employee transaction data and enterprise transaction data in multiple transaction scenarios, where different transaction scenarios correspond to different transaction identifiers.

[0066] It can be understood that employee transaction data and enterprise transaction data can be transaction data that characterize the daily life consumption of employees and enterprises, such as employee consumption data in the cafeteria, daily operating expenses of enterprises (water, electricity, network fees, etc.), and salary payment data of enterprises to employees. Employee transaction data and enterprise transaction data can be directly collected from the internal database of the financial institution system without obtaining data from external data sources, thereby improving the accuracy and efficiency of data collection. Furthermore, by analyzing employee transaction data and enterprise transaction data, more accurate and reliable indicator values ​​that characterize multiple dimensions such as the employee status, enterprise operation status, and financial status of the enterprise can be obtained, so as to achieve a comprehensive and detailed assessment of enterprise risks.

[0067] In some embodiments of this specification, obtaining the loan business data of the target enterprise and employee transaction data and enterprise transaction data in multiple transaction scenarios in step S101 may include steps S1011 and S1012, specifically:

[0068] S1011: Collecting real-time transaction log data from a target terminal and a target application in real time, and performing structured processing on the real-time transaction log data to obtain the employee transaction data.

[0069] S1012: Based on the fee payment transaction identifier, the wage payment transaction identifier, the loan identifier and the preset period, batch collect the fee payment business data, the wage payment business data and the loan business data of the target enterprise, wherein the fee payment business data and the wage payment business data are the enterprise transaction data.

[0070] It can be understood that the target terminal and the target application can be associated with each other, and the employee's daily consumption can be completed through the interaction between the target terminal and the employee's account in the target application; or the target terminal can store the employee's identification information, which can be associated with the employee's account in the target application, and then the employee's identification information can be collected through the target terminal, and the interaction between the target terminal and the employee's account in the target application can be realized through the background server, thereby completing the employee's daily consumption. Therefore, both the target application and the target terminal can contain transaction data corresponding to at least part of the employee's daily life consumption. By collecting real-time transaction log data from the target application and the target terminal respectively, the employee transaction data of the target enterprise used to characterize the employee's daily life consumption can be obtained.

[0071] It can be understood that the agency payment service can refer to a service in which a financial institution signs a relevant agreement with an enterprise and, according to the content of the agreement, acts as an agent for the enterprise to pay daily living expenses (such as water and electricity bills, telephone bills, insurance premiums, taxes, etc.). This service is usually implemented through computer network technology. The financial institution will transfer the funds to the entrusting unit by transfer or cash payment according to the collection list provided by the entrusting unit. In addition, the agency payment service data can be used as one of the basic data for assessing the risks of an enterprise. Based on the mapping relationship between the corresponding data and the indicator values ​​of the preset indicators, the indicator values ​​used to assess the daily operating expenses, operating costs, cash flow management, etc. of the enterprise can be obtained, and the risks of the target enterprise can be assessed.

[0072] It can be understood that the wage payment service data can be a service provided by commercial financial institutions to target enterprises. This service can be used to pay wages and bonuses to employees of target enterprises, and the wages can be directly transferred to employees' accounts through financial institutions. This service can make wages go directly into employees' personal bank accounts, improve the convenience and speed of payment, and reduce errors and disputes. At the same time, it can also be used as one of the basic data for assessing corporate risks. Based on the mapping relationship between the corresponding data and the indicator values ​​of the preset indicators, the indicator values ​​used to assess the company's salary payment ability, changes in the number of employees, etc. can be obtained, and then the risks of the target company can be assessed. The specific collection methods of employee transaction data, agency payment service data, and agency wage payment service data will be further introduced below and will not be repeated here.

[0073] In some embodiments of the present specification, the target terminal and the target application may be the terminal and application corresponding to the dietary management system of the target enterprise, such as a smart canteen, etc. The system can provide the enterprise with a full-process intelligent management service from employee meal ordering, canteen meal preparation, dining to settlement. Employees can use mobile applications or self-service terminals to conveniently browse menus, place orders and pay. Furthermore, by obtaining real-time transaction log data including the target terminal and the target application in the system, comprehensive, real and reliable daily life consumption data (i.e., employee transaction data) of employees in the enterprise can be collected, and then by analyzing the employee transaction data, for example, the consumption situation, attendance situation, and employee headcount change of employees in the enterprise can be obtained, and the employee transaction data is updated more frequently, which can reflect the latest situation of employees in the enterprise in real time.

[0074] In the embodiments of the present specification, the daily life flow data of the target enterprise in multiple transaction scenarios can be directly obtained from the system database by combining real-time data collection and batch data collection, and the indicator values ​​for evaluating the risks of the target enterprise from multiple dimensions can be obtained by analyzing the daily life flow data, and the target enterprise can be managed and controlled based on the corresponding indicator values, thereby improving the real-time, accuracy and reliability of post-loan risk control.

[0075] S102: Based on the transaction identifiers of the employee transaction data and the enterprise transaction data, the loan identifier of the loan business data, and the association between the transaction identifier and the loan identifier and the preset indicator, the employee transaction data, the enterprise transaction data and the loan business data are divided into multiple data sets, each data set includes at least one transaction data or at least one loan business data, and each data set corresponds to a preset indicator.

[0076] It can be understood that the calculation of the index value of each preset indicator can adopt one or more of employee transaction data, enterprise transaction data and loan business data, that is, multiple data can be integrated when calculating the index value of the preset indicator, and multiple data jointly evaluate the index value of the preset indicator dimension. Therefore, based on the association between the transaction mark and loan mark and the preset indicator, the employee transaction data, enterprise transaction data and loan business data can be divided to obtain multiple data sets, each of which can correspond to a preset indicator, and then by calculating the data in different data sets, the index values ​​of different dimensions of the target enterprise can be obtained, the risk of the target enterprise can be evaluated, and the loan business of the target enterprise can be managed and controlled.

[0077] S103: Determine the indicator value of each preset indicator based on the transaction data and / or loan business data in each data set.

[0078] In some embodiments of the present specification, there may be a mapping relationship between the indicator value and the data elements of the transaction data and / or loan business data, and based on the mapping relationship and the values ​​corresponding to each data element, the indicator value corresponding to the preset indicator may be calculated. The data elements may be, for example, transaction time, transaction amount, transaction parties, etc.

[0079] In some embodiments of the present specification, determining the indicator value of each preset indicator based on the transaction data and / or loan business data in each data set may include: determining the transaction element corresponding to each transaction data and / or the business element corresponding to the loan business data in the data set; determining the indicator value of the preset indicator corresponding to the data set based on the mapping relationship between the indicator value of the preset indicator corresponding to the data set and the transaction element and / or business element, and the element value of each transaction element and / or business element.

[0080] In some embodiments of the present specification, calculation rules for each indicator value may be preset, and the indicator value of each preset indicator may be determined based on the calculation rules corresponding to each data set and the data in the data set.

[0081] In some embodiments of this specification, the calculation rules may include the following:

[0082] Rule 1: The percentage of decrease in the number of people who consume in the smart canteen in the past week compared to the data 90 days ago on any day;

[0083] Rule 2: The percentage of decrease in the number of people who consume in the smart canteen in the past week compared to the data 365 days ago on any day;

[0084] Rule 3: The percentage of decrease in “smart canteen consumption frequency in the past week” on any day compared to the data 90 days ago;

[0085] Rule 4: The percentage of decrease in “smart canteen consumption in the past week” on any day compared to the data 90 days ago;

[0086] Rule 5: The percentage decrease in the number of people paid wages in the past month compared to the data 90 days ago on any given day;

[0087] Rule 6: The percentage decrease in the “amount of wages paid in the last month” on any given day compared to the data 90 days ago;

[0088] Rule 7: The percentage decrease in the “amount of taxes and fees paid on behalf of others in the past month” on any given day compared to the data 90 days ago;

[0089] Rule 8: The number of “historical overdue loans” in the data of any day increases compared to 30 days ago;

[0090] Rule 9: The percentage of both the "frequency of consumption in the smart canteen in the past week" and the "number of consumers in the smart canteen in the past week" decreasing compared to the data 90 days ago on any given day;

[0091] Rule 10: The percentage of both the “amount of wages paid in the past month” and the “number of people paid wages in the past month” that decreases on any given day compared to the data 90 days ago;

[0092] Rule 11: "Frequency of consumption in the smart canteen in the past week" for any day's data;

[0093] Rule 12: "Smart Canteen Consumption Amount in the Past Week" for any day's data;

[0094] Rule 13: The percentage of decrease in the “amount of salary paid in the last month” of any day’s data;

[0095] Rule 14: “Number of consumers in the smart canteen in the past week” for any day’s data;

[0096] Rule 15: The percentage of decrease in the “amount of taxes and fees paid on behalf of others in the past month” of any day’s data;

[0097] Rule 16: The percentage of decrease in the “salary payment amount in the most recent month” compared to the previous month for two consecutive months;

[0098] Rule 17: For two consecutive months, the “frequency of consumption in the smart canteen in the past week” has decreased compared to the previous month.

[0099] Furthermore, after the indicator value is calculated based on the above rules, the loan business of the target enterprise can be controlled based on the relationship between the indicator value and the indicator threshold. Taking the early warning of the target enterprise as an example, the indicator thresholds of the above rules 1 to 17 can be 10%, 50%, 15%, 20%, 10%, 15%, 20%, 1 time, 10%, 10%, 1 time / week, 50 yuan, 30%, 3 people, 25%, 10%, 10%, respectively. Except for the above rules 11 and 12, which trigger an early warning if the corresponding indicator threshold is not met, the remaining rules all trigger an early warning for the target enterprise if the corresponding indicator threshold is exceeded. Of course, in other embodiments, the above rules and / or the indicator thresholds corresponding to the rules can also be set in other ways or values, and this specification does not limit this.

[0100] S104: Based on the indicator values ​​of each preset indicator, the loan business is managed and controlled.

[0101] In some embodiments of the present specification, the loan business is managed and controlled based on the indicator values ​​of each preset indicator in step S104, which may include step S1041 and step S1042. Specifically:

[0102] S1041: Determine the risk level of the target enterprise based on the indicator value of each preset indicator and the mapping relationship between the risk level and the indicator range of each preset indicator.

[0103] S1042: Perform corresponding management and control on the loan business based on the risk level of the target enterprise.

[0104] It can be understood that different risk levels can correspond to different indicator intervals, and then based on the mapping relationship between risk levels and indicator intervals, and the multiple indicator values ​​of the target enterprise calculated, the risk level of the target enterprise can be determined, and different risk levels can correspond to different management and control measures, and then the target enterprise can be managed and controlled based on the determined risk level. The management and control can be, for example, early warning, reduction of loan amount, reduction of loan period, etc., which is not limited in this specification.

[0105] In some embodiments of the present specification, a risk level may correspond to an indicator interval of multiple preset indicators, that is, the risk level of the target enterprise is determined based on the indicator values ​​of multiple preset indicators. For example, in step S103, the indicator values ​​corresponding to the preset indicators A, B, C and D may be obtained, and the mapping relationship between the risk level and the indicator interval may be: risk level one corresponds to the indicator interval A1-A2, B1-B2, C1-C2, D1-D2, risk level two corresponds to the indicator interval A2-A3, B2-B3, C2-C3, D2-D3, and risk level three corresponds to the indicator interval A3-A4, B3-B4. The risk level of the target enterprise may be determined based on the indicator intervals satisfied by the preset indicators A, B, C and D and the mapping relationship between the indicator intervals and the risk levels.

[0106] In some embodiments of the present specification, after determining the indicator value, it is possible to judge whether each indicator value exceeds the corresponding indicator threshold based on the indicator threshold of each preset indicator, and determine the risk level of the target enterprise based on the indicator value exceeding the indicator threshold, so as to manage and control the loan business of the target enterprise.

[0107] In some embodiments of the present specification, the loan business is managed and controlled based on the indicator values ​​of each preset indicator in step S104, which may include steps S1043 to S1045, specifically:

[0108] S1043: Calculate the risk score of the target enterprise based on the indicator value of each preset indicator and the weight corresponding to each preset indicator, wherein the weight corresponding to each preset indicator is determined by the indicator data of the historical loan business.

[0109] S1044: Determine the risk level of the target enterprise based on the risk score of the target enterprise and the mapping relationship between each risk level and the risk score range.

[0110] S1045: Perform corresponding management and control on the loan business based on the risk level of the target enterprise.

[0111] In some embodiments of the present specification, the risk scoring model calculation formula can be expressed as: S = w1*L+w2*F+w3*A+w4*N+w5*W+w6*T+…, where: S can represent the risk score, L, F, A, N, W, T… can respectively represent the indicator value of each preset indicator, for example, it can respectively represent the summary of the number of historical overdue loans, the frequency of smart canteen consumption in the past week (times), the amount of smart canteen consumption in the past week (yuan), the number of smart canteen consumers in the past week (persons), the number of people who received wages in the past month (persons), the amount of wages paid in the past month (yuan), etc.; w1, w2, w3, w4, w5, w6… can respectively represent the weights of each preset indicator, and the value of each weight can be obtained through principal component analysis and machine learning algorithm.

[0112] The following introduces the calculation process of the above weights by combining principal component analysis and machine learning algorithm.

[0113] In some embodiments of the present specification, the weight of each preset indicator can be determined by principal component analysis. Specifically, a large amount of sample data can be collected and processed (i.e., the indicator data of historical loan business) to ensure the accuracy and completeness of the data; further, the sample data can be standardized to eliminate the influence of the dimension. The standardized formula can be expressed as: where z ij is the standardized value, X ij is the original data, is the mean of the jth index, S j is the standard deviation of the jth indicator. Then, the correlation coefficient matrix can be calculated. Assuming that the standardized data matrix is ​​Z, the calculation formula of the correlation coefficient matrix R can be expressed as: Where n can represent the number of samples. After that, the eigenvalues ​​and eigenvectors can be solved. Specifically, by solving the characteristic equation |λI-Z|=0 of the correlation coefficient matrix R, p eigenvalues ​​(i.e., λ1, λ2, ..., λp, p is the number of indicators) can be obtained and arranged in order from large to small. For each eigenvalue λi, solve the equation |λiI-R|=0 to obtain the corresponding eigenvector ei. Determine the principal component according to the size of the eigenvalue. Usually, the principal component with an eigenvalue greater than 1 is selected, or the number of principal components is determined according to the cumulative contribution rate (for example, the cumulative contribution rate reaches more than 80%). Suppose m principal components are selected, denoted as F1, F2, ..., Fm, then the expression of the principal component is: Where Z iis the i-th index after standardization. Calculate the variance contribution rate of each principal component: The variance contribution rate of the j-th principal component is Calculate the coefficient of each indicator in the principal component: the coefficient of the i-th indicator in the j-th principal component is e ij . Calculate the comprehensive weight of each indicator: the weight of the i-th indicator

[0114] In some embodiments of the present specification, the weight of each preset indicator can be determined by principal component analysis. Taking the calculation of weights by the random forest algorithm of machine learning as an example, specifically, multiple sample data can be collected, each sample contains the value of each preset indicator and the corresponding target variable (risk score); preprocess the data, including processing missing values, outliers, and standardizing or normalizing the numerical indicators to train the random forest model; divide the data set, and divide the preprocessed data set into a training set and a test set, for example, 80% of the data can be used as a training set and 20% of the data can be divided as a test set; use the training set to build a random forest model, specifically, the average impurity reduction method (MDI) can be used. In a random forest, each decision tree will select the feature that can minimize the impurity when splitting the node, and the importance of the feature is obtained by calculating the average impurity reduction of each feature in all decision trees. At the same time, the average accuracy reduction method (MDA) is used to randomly disrupt the value of each feature to calculate the degree of reduction in the accuracy of the model on the test set. The more the accuracy is reduced, the greater the contribution of the feature to the model and the higher the importance. Furthermore, the importance of each calculated indicator can be normalized so that its sum is 1. The normalized importance value is the weight of the indicator. According to the size of the weight, the relative importance of each indicator to the target variable can be explained. The larger the weight, the more important the role of the indicator in predicting the target variable. In some embodiments of the present specification, the importance of the summary of the number of historical overdue loans calculated by random forest is 0.3, the importance of the frequency of consumption in the smart canteen in the past week is 0.2, the importance of the amount of taxes and fees paid in the past month is 0.15, the importance of the number of consumers in the smart canteen in the past week is 0.1, the importance of the number of people paid wages in the past month is 0.1, the importance of the amount of wages paid in the past month is 0.08, and the importance of the amount of consumption in the smart canteen in the past week is 0.07. Since the above importance is combined to be 1, after normalization, the total weight of the number of overdue loans in history is 0.3; the weight of the smart canteen consumption frequency in the past week is 0.2, the importance of the amount of taxes and fees paid on behalf of others in the past month is 0.15, the importance of the number of consumers in the smart canteen in the past week is 0.1, the importance of the number of people paid wages in the past month is 0.1, the importance of the amount of wages paid in the past month is 0.08, and the importance of the amount of consumption in the smart canteen in the past week is 0.07.

[0115] In some embodiments of the present specification, performing structured processing on the real-time transaction log data to obtain the employee transaction data may include:

[0116] Establishing a data connection relationship between the real-time transaction log data and the employee transaction data, and a data transmission relationship between the real-time transaction log data of the target terminal and the real-time transaction log data of the target application;

[0117] Based on the data transmission relationship, data fusion is performed on the real-time transaction log data of the target terminal and the real-time transaction log data of the target application to obtain fused transaction log data;

[0118] Based on the data connection relationship, stream computing is performed on the fused transaction log data to obtain the employee transaction data.

[0119] In some embodiments of the present specification, the step S1011 performs structured processing on the real-time transaction log data to obtain the employee transaction data, which may include steps S11 to S14, specifically:

[0120] S11: Use Kafka to build a real-time data channel between real-time transaction log data and employee transaction data.

[0121] S12: Using Sqoop, a data transmission relationship is established between the real-time transaction log data of the target terminal and the real-time transaction log data of the target application.

[0122] S13: Based on the real-time data channel and the transmission relationship, a stream computing model is constructed using Storm.

[0123] S14: Using a stream computing model to process the real-time transaction log data to obtain the employee transaction data.

[0124] In the embodiments of this specification, the collection of smart cafeteria data can be implemented by stream computing according to the frequency of user use, so that the efficiency of obtaining key data is improved, and the efficiency of data delivery can also be improved accordingly.

[0125] In some embodiments of this specification, the employee transaction data obtained through stream computing may include the target company's smart canteen employee consumption records, meal card recharge records, consumption frequency, and consumption amount data. By analyzing employee consumption data, the consumption and attendance of the company's employees can be reflected, and the company's employee status and corporate operations can be indirectly understood.

[0126] In some embodiments of the present specification, in step S1012, based on the agency payment transaction identifier, agency salary payment transaction identifier, loan identifier and preset period, batch collection of agency payment business data, agency salary payment business data and loan business data of the target enterprise may include steps S21 and S22, specifically:

[0127] S21: construct an enterprise transaction data cluster, and construct data coordination nodes corresponding to the agency fee payment business, agency wage payment business and loan business respectively, and associate the constructed data coordination nodes with the agency fee payment transaction identifier, agency wage payment transaction identifier and loan identifier respectively.

[0128] S22: Using the data coordination node to batch collect business data associated with the corresponding data coordination node from the enterprise transaction data cluster according to a preset period, and perform structured conversion on the collected business data to obtain the payment agency business data, the salary agency business data and the loan business data.

[0129] In some embodiments of this specification, the payroll service data of the target enterprise include the number of employees paid each month, the total amount of monthly payroll, the frequency of payroll bonuses, etc. The fee payment service data of the target enterprise may include relevant data such as the water, electricity, and taxes paid on behalf of the enterprise. Various types of fee data may include a summary of the monthly payment amount, the monthly payment date and time, the payment frequency, and the data on arrears. The payroll service data can reflect the target enterprise's salary payment ability and changes in the number of employees, and can directly reflect the enterprise's operating stability and financial status. The fee payment service data can reflect the target enterprise's daily operating expenses, including the payment of water, electricity, network, etc. This information helps to understand the company's operating costs and cash flow management capabilities.

[0130] In some embodiments of the present specification, the collected structured employee transaction data can be collected in real time into the log data into the Hive database using the Hadoop 2.0 framework, and the collected payroll business data, fee payment business data, and loan business data can be stored in the MPP (Massively Parallel Processing) distributed database, and then when the indicator value is calculated later, the corresponding data can be directly obtained from the database for processing.

[0131] Data collection is achieved through the above methods. The data collected by financial institutions themselves, such as smart canteen business data, wage payment business data and fee payment business data, are derived from the actual business operations and transactions of financial institutions, and are highly authentic and reliable. The above data are directly recorded and processed by the financial institution system, which reduces the possibility of data distortion and falsification, and can quickly and accurately obtain employee transaction data and enterprise transaction data, providing a data basis for the calculation of subsequent indicator values. In addition, the above business data can cover multiple aspects of target enterprise customers and provide multi-dimensional information. Smart canteen business data, wage payment business data and fee payment business data are all generated and updated in real time based on daily business. This real-time nature helps financial institutions to grasp the operating conditions and cash flow of target enterprises in a timely manner, so as to more accurately assess their credit risks. In addition, a more comprehensive and detailed customer portrait can be constructed by integrating the above business data. For example, combining smart canteen data and wage payment data, the working status of enterprise employees and the financial health of the enterprise can be analyzed, and combining fee payment data can be used to evaluate the daily operational stability of the enterprise. Multi-dimensional analysis can improve the accuracy of enterprise risk assessment and enhance the effectiveness of risk warning.

[0132] In the embodiments of this specification, enterprise risk assessment is achieved through data collected by the financial institution itself. There is no need to frequently obtain financial statements or other supporting documents from the target enterprise. Assessment can be automatically performed through existing data. Compared with obtaining data from a third party, the use of the financial institution's own data reduces data procurement and verification costs, does not need to rely on external data sources, and can use internal data to directly perform analysis and modeling, which significantly improves the efficiency and effectiveness of risk management.

[0133] In some embodiments of this specification, the above-processed indicator values ​​and / or risk levels can be displayed through multiple channels, so that financial risk control managers who pay attention to the indicators can obtain data more efficiently. For example, the early warning data can be notified to the post-loan management personnel of the financial institution through means such as data large screens and mobile terminal message reminders, thereby reducing the occurrence of overdue and bad corporate loans.

[0134] Combine the following Figure 2 The above data processing method in some embodiments of this specification is further introduced. Figure 2As shown in the figure, after collecting data through application services, two sets of API (Application Programming Interface) data collection gateways can be used to collect accounting transactions and APP page embedding data in the smart canteen. Loan business, wage payment and payment business are collected in batch files on T+1 day. In terms of data storage, the Hadoop 2.0 framework is used to collect real-time log data into the Hive database, Flume service is used as a tool for log collection, Kafka is used to build a real-time data channel, and Sqoop is used to establish a data transmission relationship between real-time data tables, and the Storm program is used to build a stream computing model. For batch-collected loan, payment and payment data, by building a CM (Cluster Manager) cluster, setting up 3 data CN (Coordinator Node) transmission nodes, enter the MPP distributed database. At the data service layer, open source Python tools, R tools and MySQL tools are used to process data, and Echart visualization tools are used to convert data into real-time visualization charts. In terms of data presentation, the processed data will be communicated to the staff responsible for risk control through four channels: large data screen, mobile dashboard APP, corporate WeChat account, and text messages.

[0135] In some embodiments of this specification, the data service layer can process data based on the data flow table of seven key indicators associated and integrated with the smart canteen business, wage payment business, fee payment business, and credit overdue record data (i.e., loan business data), including: the summary of the number of historical overdue loans (unit: times), the frequency of smart canteen consumption in the past week (unit: times), the amount of smart canteen consumption in the past week (unit: yuan), the number of smart canteen consumers in the past week (unit: person), the number of people paid wages in the past month (unit: person), the amount of wages paid in the past month (unit: yuan), and the amount of taxes and fees paid on behalf of the past month (unit: yuan). The relevant data is calculated and collected every day into the data table: Dininghall_wage_payfee_badloan_forecast. The data table can record the field name, data type, field description, and field value of each field. The calculation of each field value can refer to the calculation of the indicator value in the previous text, which will not be repeated here.

[0136] Compared with the traditional credit risk control that only relies on credit records and financial statements, the embodiments of this specification introduce data sources of smart canteens, wage payment and fee payment services, forming a multi-dimensional and multi-level data coverage. Smart canteen data can provide information on consumption habits, frequency and amount of target enterprises, reflecting the stability and consumption capacity of target enterprises in daily operations. Payroll payment can directly reflect the income level, job stability and employment status of employees in the target enterprise, which helps to evaluate the repayment ability of the enterprise. Paying taxes and fees on behalf of others can help understand the tax situation of the target enterprise and help financial institutions obtain business information in a timely manner. The above method can realize rapid updating and monitoring of data, and improve the timeliness and effectiveness of risk warning. Based on the latest data, the risk control strategy can be adjusted in real time, potential risks can be discovered in time, and lag problems can be avoided. Compared with the traditional risk control model using a highly universal scoring model, the embodiment of this specification can achieve accurate evaluation and differentiated management of target enterprises by refining data indicators.

[0137] Based on the data processing method described above, one or more embodiments of this specification also provide a data processing device. The device may include a device (including a distributed system), software (application), module, plug-in, server, client, etc. using the method described in the embodiment of this specification and combined with a device of necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiment of this specification is as described in the following embodiments. Since the implementation scheme and method for solving the problem of the device are similar, the implementation of the specific device of the embodiment of this specification can refer to the implementation of the aforementioned method, and the repetitions are not repeated. As used below, the term "unit" or "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived. Figure 3 FIG. 1 is a schematic diagram of a data processing device provided in an embodiment of this specification. Figure 3 As shown, the data processing device 300 may include a data acquisition module 301 , a data partitioning module 302 , a data processing module 303 and a management and control module 304 .

[0138] The data acquisition module 301 is used to respond to a monitoring request for the loan business of a target enterprise, obtain the loan business data of the target enterprise and employee transaction data and enterprise transaction data under multiple transaction scenarios, and different transaction scenarios correspond to different transaction identifiers.

[0139] The data partitioning module 302 is used to partition the employee transaction data, the enterprise transaction data and the loan business data into multiple data sets based on the transaction identifiers of the employee transaction data and the enterprise transaction data, the loan identifier of the loan business data, and the association between the transaction identifier and the loan identifier and the preset indicator, each data set includes at least one transaction data or at least one loan business data, and each data set corresponds to a preset indicator.

[0140] The data processing module 303 is used to determine the indicator value of each preset indicator based on the transaction data and / or loan business data in each data set.

[0141] The control module 304 is used to control the loan business based on the indicator values ​​of each preset indicator.

[0142] In some embodiments of the present specification, when acquiring the target enterprise's loan business data and employee transaction data and enterprise transaction data in multiple transaction scenarios, the data acquisition module 301 can be specifically used to: collect real-time transaction log data from the target terminal and the target application in real time, and perform structured processing on the real-time transaction log data to obtain the employee transaction data. Then, based on the agency payment transaction identifier, agency salary transaction identifier, loan identifier and preset cycle, the agency payment business data, agency salary business data and loan business data of the target enterprise can be batch collected, wherein the agency payment business data and agency salary business data are the enterprise transaction data.

[0143] In some embodiments of the present specification, when the data acquisition module 301 performs structured processing on the real-time transaction log data to obtain the employee transaction data, it can be specifically used to: construct a data connection relationship between the real-time transaction log data and the employee transaction data, and a data transmission relationship between the real-time transaction log data of the target terminal and the real-time transaction log data of the target application. Further, the real-time transaction log data of the target terminal and the real-time transaction log data of the target application can be data fused based on the data transmission relationship to obtain fused transaction log data. Afterwards, stream computing can be performed on the fused transaction log data based on the data connection relationship to obtain the employee transaction data.

[0144] In some embodiments of the present specification, when the data acquisition module 301 performs structured processing on the real-time transaction log data to obtain the employee transaction data, it can be specifically used to: use Kafka to build a real-time data channel between the real-time transaction log data and the employee transaction data. Then, use Sqoop to establish a data transmission relationship between the real-time transaction log data of the target terminal and the real-time transaction log data of the target application. Afterwards, based on the real-time data channel and the transmission relationship, use Storm to build a stream computing model. Further, the stream computing model can be used to process the real-time transaction log data to obtain the employee transaction data.

[0145] In some embodiments of the present specification, when the data acquisition module 301 collects the fee payment agency business data, wage payment agency business data and loan business data of the target enterprise in batches based on the fee payment agency transaction identifier, wage payment agency transaction identifier, loan identifier and preset period, it can be specifically used to: construct an enterprise transaction data cluster, and construct data coordination nodes corresponding to the fee payment agency business, wage payment agency business and loan business respectively, and associate the constructed data coordination nodes with the fee payment agency transaction identifier, wage payment agency transaction identifier and loan identifier respectively. After the data coordination nodes are constructed, the data coordination nodes can be used to batch collect business data of the identifier associated with the corresponding data coordination node from the enterprise transaction data cluster according to the preset period, and the collected business data is structured to obtain the fee payment agency business data, the wage payment agency business data and the loan business data.

[0146] In some embodiments of the present specification, the data processing module 303 is specifically used to determine the index value of each preset index based on the transaction data and / or loan business data in each data set: determine the transaction element corresponding to each transaction data and / or the business element corresponding to the loan business data in the data set. Then, the index value of the preset index corresponding to the data set can be determined based on the mapping relationship between the index value of the preset index corresponding to the data set and the transaction element and / or business element, and the element value of each transaction element and / or business element.

[0147] In some embodiments of the present specification, the control module 304 can be specifically used to determine the risk level of the target enterprise based on the indicator value of each preset indicator and the mapping relationship between the risk level and the indicator interval of each preset indicator. Further, the loan business can be controlled accordingly based on the risk level of the target enterprise.

[0148] In some embodiments of the present specification, the management and control module 304 can be specifically used to: calculate the risk score of the target enterprise based on the indicator values ​​of each preset indicator; determine the risk level of the target enterprise based on the risk score of the target enterprise and the mapping relationship between each risk level and the risk score interval; and perform corresponding management and control on the loan business based on the risk level of the target enterprise.

[0149] The description and functions of the above modules can be understood by referring to the content of the data processing method part, which will not be repeated here.

[0150] The present application also provides an electronic device, such as Figure 4 As shown, the electronic device 400 may include a processor 401 and a memory 402, wherein the processor 401 and the memory 402 may be connected via a bus 403 or other means. Figure 4 The connection via bus 403 is taken as an example.

[0151] In some embodiments of the present specification, the processor 401 may be a central processing unit (CPU). In other embodiments, the processor 401 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0152] The memory 402 is a non-transitory computer-readable storage medium that can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the data processing method in the embodiment of the present application (for example, Figure 3 The processor 401 executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory 402, that is, the data processing method in the above method embodiment is implemented.

[0153] The memory 402 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the processor 401, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 402 may optionally include a memory remotely arranged relative to the processor 401, and these remote memories may be connected to the processor 401 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0154] The one or more modules are stored in the memory 402, and when executed by the processor 401, perform the following data processing method:

[0155] In response to a monitoring request for a target enterprise's loan business, obtaining the target enterprise's loan business data and employee transaction data and enterprise transaction data under multiple transaction scenarios, where different transaction scenarios correspond to different transaction identifiers;

[0156] Based on the transaction identifiers of the employee transaction data and the enterprise transaction data, the loan identifier of the loan business data, and the association between the transaction identifier and the loan identifier and the preset indicator, the employee transaction data, the enterprise transaction data, and the loan business data are divided into a plurality of data sets, each of which includes at least one transaction data or at least one loan business data, and each data set corresponds to a preset indicator;

[0157] Determine the indicator value of each preset indicator based on the transaction data and / or loan business data in each data set;

[0158] Based on the indicator values ​​of each preset indicator, the loan business is managed and controlled.

[0159] The specific details of the electronic device 400 can be understood by referring to the corresponding descriptions and effects in the above method embodiments, which will not be repeated here.

[0160] The present specification also provides a computer storage medium, wherein the computer storage medium stores computer program instructions, and the computer program instructions implement the steps of the above data processing method when executed.

[0161] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0162] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0163] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions.

[0164] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0165] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute certain parts of the methods of each implementation method of the present application.

[0166] The present application can be used in many general or special computer system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0167] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0168] Although the present application has been described through embodiments, those skilled in the art will appreciate that there are many modifications and variations to the present application without departing from the spirit of the present application, and it is intended that the appended claims include these modifications and variations without departing from the spirit of the present application.

Claims

1. A data processing method, characterized in that: include: In response to a monitoring request for a target enterprise's loan business, obtaining the target enterprise's loan business data and employee transaction data and enterprise transaction data under multiple transaction scenarios, where different transaction scenarios correspond to different transaction identifiers; Based on the transaction identifiers of the employee transaction data and the enterprise transaction data, the loan identifier of the loan business data, and the association between the transaction identifier and the loan identifier and the preset indicator, the employee transaction data, the enterprise transaction data, and the loan business data are divided into a plurality of data sets, each of which includes at least one transaction data or at least one loan business data, and each of which corresponds to a preset indicator; Determine the indicator value of each preset indicator based on the transaction data and / or loan business data in each data set; Based on the indicator values ​​of each preset indicator, the loan business is managed and controlled.

2. The method according to claim 1, characterized in that Obtain the target enterprise's loan business data and employee transaction data and enterprise transaction data in multiple transaction scenarios, including: Collecting real-time transaction log data from a target terminal and a target application in real time, and performing structured processing on the real-time transaction log data to obtain the employee transaction data; Based on the fee payment transaction identifier, the wage payment transaction identifier, the loan identifier and the preset period, the fee payment business data, the wage payment business data and the loan business data of the target enterprise are collected in batches, wherein the fee payment business data and the wage payment business data are the enterprise transaction data.

3. The method according to claim 2, characterized in that The real-time transaction log data is structured to obtain the employee transaction data, including: Establishing a data connection relationship between the real-time transaction log data and the employee transaction data, and a data transmission relationship between the real-time transaction log data of the target terminal and the real-time transaction log data of the target application; Based on the data transmission relationship, data fusion is performed on the real-time transaction log data of the target terminal and the real-time transaction log data of the target application to obtain fused transaction log data; Based on the data connection relationship, stream computing is performed on the fused transaction log data to obtain the employee transaction data.

4. The method according to claim 2 or 3, characterized in that: The real-time transaction log data is structured to obtain the employee transaction data, including: Use Kafka to build a real-time data channel between real-time transaction log data and employee transaction data; Using Sqoop to establish a data transmission relationship between the real-time transaction log data of the target terminal and the real-time transaction log data of the target application; Based on the real-time data channel and the transmission relationship, a stream computing model is constructed using Storm; The real-time transaction log data is processed using a stream computing model to obtain the employee transaction data.

5. The method according to claim 2, characterized in that: Based on the agency fee payment transaction identifier, agency wage payment transaction identifier, loan identifier and preset period, the agency fee payment business data, agency wage payment business data and loan business data of the target enterprise are collected in batches, including: Constructing enterprise transaction data clusters, and constructing data coordination nodes corresponding to the agency payment business, agency salary payment business, and loan business respectively, and associating the constructed data coordination nodes with the agency payment transaction identifier, agency salary payment transaction identifier, and loan identifier respectively; The data coordination node is used to batch collect business data associated with the corresponding data coordination node from the enterprise transaction data cluster according to a preset period, and the collected business data is structured to obtain the payment agency business data, the salary agency business data and the loan business data.

6. The method according to claim 1, characterized in that Based on the transaction data and / or loan business data in each data set, determine the indicator value of each preset indicator, including: Determine the transaction elements corresponding to each transaction data and / or the business elements corresponding to the loan business data in the data set; Based on the mapping relationship between the indicator value of the preset indicator corresponding to the data set and the transaction elements and / or business elements, and the element value of each transaction element and / or business element, the indicator value of the preset indicator corresponding to the data set is determined.

7. The method according to claim 1, characterized in that Based on the indicator values ​​of each preset indicator, the loan business is controlled, including: Determine the risk level of the target enterprise based on the indicator value of each preset indicator and the mapping relationship between the risk level and the indicator range of each preset indicator; The loan business is managed and controlled accordingly based on the risk level of the target enterprise.

8. The method according to claim 1, characterized in that Based on the indicator values ​​of each preset indicator, the loan business is controlled, including: Calculating the risk score of the target enterprise based on the indicator value of each preset indicator and the weight corresponding to each preset indicator, wherein the weight corresponding to each preset indicator is determined by the indicator data of the historical loan business; Determine the risk level of the target enterprise based on the risk score of the target enterprise and the mapping relationship between each risk level and the risk score range; The loan business is managed and controlled accordingly based on the risk level of the target enterprise.

9. A data processing device, characterized in that: include: A data acquisition module, for responding to a monitoring request for a target enterprise's loan business, acquiring the target enterprise's loan business data and employee transaction data and enterprise transaction data under multiple transaction scenarios, where different transaction scenarios correspond to different transaction identifiers; a data partitioning module, configured to partition the employee transaction data, the enterprise transaction data, and the loan business data into a plurality of data sets based on the transaction identifiers of the employee transaction data and the enterprise transaction data, the loan identifiers of the loan business data, and the association between the transaction identifiers and the loan identifiers and the preset indicators, each data set including at least one transaction data or at least one loan business data, and each data set corresponding to a preset indicator; A data processing module, used to determine the index value of each preset index based on the transaction data and / or loan business data in each data set; The control module is used to control the loan business based on the indicator values ​​of each preset indicator.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor implements the steps of the method according to any one of claims 1 to 8 by executing the computer instructions.

11. A computer storage medium, characterized in that: The computer storage medium stores computer program instructions, and when the computer program instructions are executed, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the steps of the method according to any one of claims 1 to 8 when being executed by a processor.

Images