Online due diligence processing method and device

Abstract

The present disclosure provides an online due diligence processing method, which is applied to the field of financial technology. The method includes: obtaining the preset risk characterization information of the financing request object; determining at least one risk quantification label associated with the financing request object based on the risk characterization information; determining a set of projects to be adjusted that are applicable to the financing request object according to the at least one risk quantification label; returning the set of projects to be adjusted to the financing request object so that the financing request object uploads registration data based on the set of projects to be adjusted; determining the credit line associated with the financing request object based on the obtained registration data, and returning the credit line to the bank financing platform so that the bank financing platform can perform a lending operation based on the credit line. The present disclosure also provides an online due diligence processing device, an electronic device, and a computer storage medium.

Description

Technical Field

[0001] The present disclosure relates to the field of online credit technology, and in particular to an online due diligence processing method and device. Background Art

[0002] Due diligence (i.e. due diligence) is an essential part of risk control in bank credit business. In recent years, with the rapid development of online micro-financing business, the number of micro-financial customers and business volume of banks have shown a rapid growth trend, which has put forward new requirements for due diligence efficiency and convenience.

[0003] In the process of implementing the technical solution disclosed in the present invention, the inventors found that in the related technologies, risk control personnel often obtain on-site record data through on-site due diligence. This method has the problems of low due diligence efficiency and poor due diligence convenience, and it cannot adapt well to the requirements of small and micro financing business. Summary of the invention

[0004] One aspect of the present disclosure provides an online due diligence processing method, including: obtaining preset risk characterization information of a financing request object; determining at least one risk quantification label associated with the financing request object based on the risk characterization information; determining a set of projects to be adjusted that are applicable to the financing request object according to the at least one risk quantification label; returning the set of projects to be adjusted to the financing request object, so that the financing request object uploads registration data based on the set of projects to be adjusted; determining a credit line associated with the financing request object based on the obtained registration data, and returning the credit line to a bank financing platform, so that the bank financing platform can perform a lending operation based on the credit line.

[0005] Optionally, determining the set of projects to be adjusted that are suitable for the object of the financing request based on the at least one risk quantification label includes: determining a target due diligence model that has the highest degree of match with the at least one risk quantification label, the target due diligence model being preset with at least one risk reference label, and the degree of match between the at least one risk reference label and the at least one risk quantification label is the highest; using the set of projects to be adjusted associated with the target due diligence model as the set of projects to be adjusted that are suitable for the object of the financing request.

[0006] Optionally, returning the set of items to be adjusted to the financing request object so that the financing request object uploads registration data based on the set of items to be adjusted includes: generating a personalized document file according to the set of items to be adjusted; returning the personalized document file to the financing request object so that the financing request object uploads the registration data according to the personalized document file; wherein, the manner of uploading the registration data includes at least one of the following: uploading the registration data using image transmission technology; uploading the registration data using image recognition technology; uploading the registration data using voice recognition technology; uploading the registration data using online editing technology.

[0007] Optionally, before determining at least one risk quantification label associated with the financing request object based on the risk characterization information, the method further includes: determining a risk estimation score for the financing request object based on the risk characterization information; obtaining risk estimation reference data associated with the financing request object from a preset data source; adjusting the risk estimation score based on the risk estimation reference data to obtain a risk quantification score for the financing request object; and generating an online due diligence task for the financing request object when the risk quantification score is lower than a preset threshold.

[0008] Optionally, before determining the credit line associated with the financing request object based on the acquired registration data, it also includes: receiving on-site record data obtained by risk control personnel through on-site due diligence; determining the difference measurement value between the registration data and the on-site record data based on preset data weights and scaling factors; and when the difference measurement value is lower than a preset threshold, executing the operation of determining the credit line.

[0009] Optionally, when the difference measurement value is lower than a preset threshold, executing the operation of determining the credit limit includes: performing a business logic check on the financing request object based on the acquired registration data; and when the business logic check passes, determining the credit limit based on the registration data.

[0010] Optionally, before determining the risk estimation score of the financing request object based on the risk characterization information, the method further includes: performing a blacklist check on the financing request object; and if the financing request object is not on a preset blacklist, performing an operation of determining the risk estimation score.

[0011] Optionally, the risk characterization information includes at least one of the following: enterprise entity information, financial account information, company product information, usage and priority, and policy support content.

[0012] Another aspect of the present disclosure provides an online due diligence processing device, including: an acquisition module, used to acquire preset risk characterization information of a financing request object; a first processing module, used to determine at least one risk quantification label associated with the financing request object based on the risk characterization information; a second processing module, used to determine a set of projects to be adjusted that are applicable to the financing request object according to the at least one risk quantification label; a third processing module, used to return the set of projects to be adjusted to the financing request object, so that the financing request object uploads registration data based on the set of projects to be adjusted; a fourth processing module, used to determine a credit line associated with the financing request object based on the acquired registration data, and return the credit line to a bank financing platform, so that the bank financing platform can perform a lending operation based on the credit line.

[0013] Optionally, the second processing module includes: a first processing sub-module, used to determine the target due diligence model with the highest matching degree with the at least one risk quantification label, the target due diligence model is preset with at least one risk reference label, and the matching degree between the at least one risk reference label and the at least one risk quantification label is the highest; a second processing sub-module, used to use the set of projects to be adjusted associated with the target due diligence model as the set of projects to be adjusted applicable to the financing request object.

[0014] Optionally, the third processing module includes: a third processing submodule, used to generate a personalized document file according to the set of items to be adjusted; a fourth processing submodule, used to return the personalized document file to the financing request object, so that the financing request object uploads the registration data according to the personalized document file; wherein, the method of uploading the registration data includes at least one of the following: uploading the registration data using image transmission technology; uploading the registration data using image recognition technology; uploading the registration data using voice recognition technology; uploading the registration data using online editing technology.

[0015] Optionally, the device also includes: a fifth processing module, used to determine the risk estimation score of the financing request object based on the risk characterization information; obtain risk estimation reference data associated with the financing request object from a preset data source; perform adjustment processing on the risk estimation score according to the risk estimation reference data to obtain a risk quantification score of the financing request object; and generate an online due diligence task for the financing request object when the risk quantification score is lower than a preset threshold.

[0016] Optionally, the fourth processing module includes: a fifth processing sub-module, used to receive on-site record data obtained by risk control personnel through on-site due diligence; determine the difference measurement value between the registration data and the on-site record data according to preset data weights and scaling factors; and when the difference measurement value is lower than a preset threshold, execute the operation of determining the credit limit.

[0017] Optionally, the fourth processing module also includes: a sixth processing sub-module, used to perform a business logic check on the financing request object according to the acquired registration data; and when the business logic check passes, determine the credit limit based on the registration data.

[0018] Optionally, the fifth processing module is further configured to perform a blacklist check on the object of the financing request; and if the object of the financing request is not on a preset blacklist, perform an operation of determining the risk estimation score.

[0019] Optionally, the risk characterization information includes at least one of the following: enterprise entity information, financial account information, company product information, usage and priority, and policy support content.

[0020] Another aspect of the present disclosure provides an electronic device, comprising one or more processors; and a memory 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 implement the method of an embodiment of the present disclosure.

[0021] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the method of the embodiment of the present disclosure when executed.

[0022] Another aspect of the present disclosure provides a computer program product, including computer-readable instructions, wherein the computer-readable instructions are used to execute the online due diligence processing method of an embodiment of the present disclosure when executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] For a more complete understanding of the present disclosure and its advantages, reference will now be made to the following description taken in conjunction with the accompanying drawings, in which:

[0024] Figure 1 The system architecture of the online due diligence processing method and device according to an embodiment of the present disclosure is schematically shown;

[0025] Figure 2 A flowchart of an online due diligence processing method according to an embodiment of the present disclosure is schematically shown;

[0026] Figure 3A flowchart of another online due diligence processing method according to an embodiment of the present disclosure is schematically shown;

[0027] Figure 4 A schematic diagram of an online due diligence processing system according to an embodiment of the present disclosure is schematically shown;

[0028] Figure 5 A schematic diagram of information processing of an interaction module according to an embodiment of the present disclosure is schematically shown;

[0029] Figure 6 A schematic diagram of information processing of a business processing module according to an embodiment of the present disclosure is shown schematically;

[0030] Figure 7 A schematic diagram of information processing of a data model module according to an embodiment of the present disclosure is schematically shown;

[0031] Figure 8 A schematic diagram of information processing of a parameter configuration module according to an embodiment of the present disclosure is shown schematically;

[0032] Fig. 9 A block diagram of an online due diligence processing device according to an embodiment of the present disclosure is schematically shown;

[0033] Fig.10 A block diagram of an electronic device according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0034] 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.

[0035] Some block diagrams and / or flow charts are shown in the accompanying drawings. It should be understood that some boxes or combinations thereof in the block diagrams and / or flow charts can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable online due diligence processing device, so that these instructions can create a device for implementing the functions / operations described in these block diagrams and / or flow charts when executed by the processor. The technology of the present disclosure can be implemented in the form of hardware and / or software (including firmware, microcode, etc.). In addition, the technology of the present disclosure can take the form of a computer program product on a computer-readable storage medium storing instructions, which can be used by an instruction execution system or in combination with an instruction execution system.

[0036] The embodiment of the present disclosure provides an online due diligence processing method and a processing device capable of applying the method. The method may specifically include the following operations: first, obtaining the preset risk characterization information of the financing request object; then, based on the risk characterization information, determining at least one risk quantification label associated with the financing request object; and determining the set of projects to be adjusted that are applicable to the financing request object according to the at least one risk quantification label; next, returning the set of projects to be adjusted to the financing request object, so that the financing request object uploads registration data based on the set of projects to be adjusted; finally, determining the credit limit associated with the financing request object according to the obtained registration data, and returning the credit limit to the bank financing platform, so that the bank financing platform can perform a lending operation based on the credit limit.

[0037] Figure 1 The system architecture of the online due diligence processing method and device according to the embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0038] like Figure 1 As shown, the system architecture 100 includes a terminal (multiple terminals are shown in the figure, such as terminals 101, 102, and 103) and a server (such as server 104), and the server is connected to the application end in communication. Server 104 can be a due diligence server for performing online due diligence tasks in a bank financing platform, or it can be a third-party server for performing online due diligence tasks independent of the bank financing platform. It is worth noting that other servers or processors that can perform online due diligence processing are within the scope of protection of this application.

[0039] The server 104 obtains preset risk characterization information of a type from the terminal (such as terminals 101, 102, 103) of the financing request object. Then, based on the risk characterization information, the server 104 determines at least one risk quantification label associated with the financing request object, and determines a set of pending projects applicable to the financing request object according to the at least one risk quantification label. Next, the server 104 returns the pending project set to the terminal (such as terminals 101, 102, 103) of the financing request object, so that the financing request object uploads registration data based on the pending project set. Finally, the server 104 determines the credit line associated with the financing request object based on the obtained registration data, and returns the credit line to the bank financing platform, so that the bank financing platform can perform lending operations based on the credit line.

[0040] It should be noted that the online due diligence processing method and device of the embodiment of the present disclosure can be used in the financial field, and can also be used in any field other than the financial field. The present disclosure will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0041] Figure 2 The flowchart of an online due diligence processing method according to an embodiment of the present disclosure is schematically shown. Figure 2 As shown, method 200 may include operations S210 to S250.

[0042] In operation S210, preset risk characterization information of a financing request object is obtained.

[0043] In the disclosed embodiment, specifically, the risk characterization information of the financing request object is obtained, and the risk characterization information includes at least one of the following: enterprise subject information, financial subject information, company product information, purpose and priority, and policy support content. Enterprise subject information may include, for example, information such as the enterprise registration area and the enterprise operation time, financial subject information may include, for example, information such as the enterprise registered capital and the enterprise operation flow, company product information may include, for example, information such as the company product type and product scale, purpose and priority may include, for example, information such as the company product purpose and the industry type, and policy support content may include, for example, policy content such as national credit relaxation, tightening, and support.

[0044] Risk characterization information is used to conduct preliminary risk classification and risk quantification assessment on the object of financing request. Risk characterization information can be part of the items to be adjusted for online credit business. The specific method of obtaining risk characterization information can be that the object of financing request transmits it to the due diligence server through online data transmission, or the due diligence server obtains it from online data sources such as the National Enterprise Information Publicity System.

[0045] Next, in operation S220, at least one risk quantification label associated with the financing request object is determined based on the risk characterization information.

[0046] In the disclosed embodiment, specifically, based on the acquired risk characterization information, the financing request object is labeled and classified, and the risk classification and risk quantification assessment of the financing request object are realized, and at least one risk quantification label for characterizing the credit risk information of the financing request object is obtained. Exemplarily, the risk quantification label may include a medium-sized customer with a registered area of ​​Beijing and an operating capital of 100,000 to 200,000 yuan, agricultural product production type, and a national key support project in 2020.

[0047] Next, in operation S230, a set of pending projects applicable to the financing request object is determined according to at least one risk quantification tag.

[0048] In the disclosed embodiment, specifically, according to the determined at least one risk quantification label, a set of projects to be adjusted for online due diligence of the object of the financing request is determined. The set of projects to be adjusted is a set of due diligence information used for loan risk assessment and credit limit determination, and specifically may include multi-dimensional data of the object of the financing request, for example, the enterprise entity information, asset and liability information, financial account information, enterprise business information, upstream and downstream merchant information, etc. of the object of the financing request.

[0049] Specifically, the enterprise entity information may include, for example, the judicial data, industrial and commercial data, enterprise shareholder data, enterprise human resources data and other information of the financing request object; the asset and liability information may include, for example, the enterprise asset information, enterprise liability information, loss rate asset characteristics and other information of the financing request object; the financial account information may include, for example, the enterprise asset statement, enterprise income statement, enterprise balance sheet and other information; the enterprise business information may include, for example, the enterprise order data, invoice data, transaction data, inventory amount and other information; the upstream and downstream merchant information may include, for example, the merchant information, order data, transaction amount and other information that have upstream and downstream business relationships with the financing request object.

[0050] The collection of projects to be investigated includes information such as the types of materials required for due diligence, types of non-required materials, the filling templates corresponding to each type of materials, and the effective duration of due diligence. The types of materials required for due diligence can be formulated by business experts based on business compliance considerations and in accordance with regulations and systems. Specifically, the required materials for due diligence can be imported in batches in the form of structured data. The types of non-required materials can be flexibly configured by risk control personnel of each business line according to the risk control needs of the product line in the region. The filling template is automatically generated according to the types of due diligence materials, and risk control personnel can adjust the layout of the filling template to optimize the user experience when registering materials.

[0051] Next, in operation S240, the set of projects to be adjusted is returned to the financing request object, so that the financing request object uploads registration data based on the set of projects to be adjusted.

[0052] In the disclosed embodiment, specifically, the set of items to be adjusted is returned to the financing request object, and specifically, the set of items to be adjusted can be returned to the financing request object in the form of a personalized document file, so that the financing request object uploads the registration data based on the personalized document file. The financing request object can pass the registration data online to the due diligence server through the interactive platform. This design can effectively shorten the network credit due diligence cycle, which is conducive to improving the efficiency of credit due diligence and improving the convenience of due diligence. It can well adapt to the rapid development requirements of online micro-financing business.

[0053] Next, in operation S250, the credit limit associated with the financing request object is determined based on the acquired registration data, and the credit limit is returned to the bank financing platform so that the bank financing platform can perform a lending operation based on the credit limit.

[0054] In the disclosed embodiment, specifically, the preset credit line calculation model is used to evaluate the asset-liability of the financing request object based on the acquired multi-dimensional registration data to determine the credit line applicable to the financing request object. The due diligence server returns the credit line to the bank financing platform so that the bank financing platform can perform the lending operation based on the acquired credit line. Optionally, after the loan is successfully granted to the financing request object, a credit abnormality warning can be issued based on the repayment status of the financing request object and the overall asset performance of the financing request object in each preset time period.

[0055] In the disclosed embodiment, the preset risk characterization information of the financing request object is obtained; based on the risk characterization information, at least one risk quantification label associated with the financing request object is determined; according to the at least one risk quantification label, a set of projects to be adjusted applicable to the financing request object is determined; the set of projects to be adjusted is returned to the financing request object, so that the financing request object uploads registration data based on the set of projects to be adjusted; according to the obtained registration data, the credit line associated with the financing request object is determined, and the credit line is returned to the bank financing platform, so that the bank financing platform can perform a lending operation based on the credit line. By determining at least one risk quantification label associated with the financing request object, and determining the set of projects to be adjusted applicable to the financing request object based on the at least one risk quantification label, so that the financing request object uploads registration data online based on the set of projects to be adjusted, it can be achieved that while providing an effective risk reference basis for the bank financing platform, the labor cost consumption of the risk control personnel for offline due diligence can be effectively reduced, and the workload of offline credit line evaluation can be effectively reduced, which is conducive to effectively improving the due diligence efficiency of small and micro financing business, and effectively improving the convenience of due diligence of credit risk control, and can fully meet the requirements of the rapid development of online small and micro financing business.

[0056] Figure 3 The flowchart of another online due diligence processing method according to an embodiment of the present disclosure is schematically shown. Figure 3 As shown, the method 300 may include operations S210 ˜ S220 , S310 ˜ S320 , and S250 .

[0057] In operation S210, preset risk characterization information of a financing request object is obtained.

[0058] In this embodiment, specifically, after obtaining the risk characterization information of the object of the financing request, the object of the financing request can be checked on the blacklist based on the risk characterization information. Specifically, the basic information of the object of the financing request can be used as a search condition to search in a preset blacklist, which can be a bank's internal blacklist or a list of dishonest enterprises or a blacklist of abnormal operations provided by the national enterprise information disclosure system. In the case of determining that the object of the financing request is not on the preset blacklist, the subsequent operation of determining the risk estimation score of the object of the financing request is performed. By checking the blacklist of the object of the financing request, it is beneficial to further improve the efficiency of credit due diligence, and by timely excluding the blacklisted financing request objects, it is beneficial to avoid the waste of resources caused by the execution of invalid due diligence tasks.

[0059] After determining that the object of the financing request is not a blacklisted customer, the risk estimation score of the object of the financing request can be determined based on the acquired risk characterization information. Further, the risk estimation reference data associated with the object of the financing request can be obtained from the preset data source, and the risk estimation score can be adjusted according to the risk estimation reference data to obtain the risk quantification score of the object of the financing request, and the risk quantification score indicates the risk level of the object of the financing request. When the risk quantification score is lower than the preset threshold, an online due diligence task for the object of the financing request is generated. The risk estimation reference data can, for example, include the credit rating score of the object of the financing request by other financial platforms, or can also include the industrial and commercial data, credit data and other contents of the object of the financing request in other data sources, wherein the credit data can, for example, include information such as credit rating, loan balance, number of settled businesses, number of overdue businesses, number of bad businesses, etc. When the risk quantification score indicates that the risk level of the object of the financing request is medium or above, the online due diligence service can be refused for the object of the financing request.

[0060] Next, in operation S220, at least one risk quantification label associated with the financing request object is determined based on the risk characterization information.

[0061] Next, in operation S310, a target due diligence model having the highest matching degree with at least one risk quantification tag is determined, and a set of projects to be adjusted associated with the target due diligence model is used as a set of projects to be adjusted applicable to the financing request object.

[0062] In this embodiment, specifically, a target due diligence model with the highest matching degree with at least one risk quantification label is determined, the target due diligence model is preset with at least one risk reference label, and the matching degree between at least one risk reference label of the target due diligence model and at least one risk quantification label is the highest. The set of projects to be adjusted associated with the target due diligence model is used as the set of projects to be adjusted applicable to the financing request object.

[0063] In actual applications, risk control strategies can be configured based on rule factors to form a variety of due diligence models, wherein each due diligence model is preset with at least one risk reference label. When determining the set of pending projects applicable to the financing request object, at least one risk quantification label associated with the financing request object can be used to determine the risk reference label cluster with the highest degree of match with at least one risk quantification label, thereby determining the target due diligence model with the highest degree of match with at least one risk quantification label. Among them, at least one risk reference label preset in each due diligence model can be formulated by business experts according to the requirements of rules and regulations. In actual online due diligence tasks, risk control personnel can flexibly configure the pending projects in the pending project set according to the risk control needs of the product line in the region, and form personalized document files in the form of electronic documents.

[0064] Next, in operation S320, a personalized document file is generated according to the set of items to be transferred, and the personalized document file is returned to the financing request object, so that the financing request object uploads registration data according to the personalized document file.

[0065] In this embodiment, after generating a personalized document file according to the set of items to be adjusted, the personalized document file is returned to the financing request object, so that the financing request object uploads registration data according to the personalized document file. The way of uploading registration data includes at least one of the following: uploading registration data using image transmission technology; uploading registration data using image recognition technology; uploading registration data using voice recognition technology; uploading registration data using online editing technology.

[0066] The personalized document file includes a filling template formed based on the set of projects to be adjusted. The financing request object can transmit the registration data to the due diligence server online based on the received personalized document file. Specifically, the due diligence server can obtain the registration data of the financing request object through image transmission technologies such as picture transmission, video transmission, and video call. Alternatively, image recognition technology can also be used to identify the electronic documents or paper materials provided by the financing request object to reduce the time-consuming manual input of large amounts of data and reduce the risk of input errors. In addition, voice recognition technology can also be used to identify the voice content uploaded by the financing request object. At the same time, voice recognition technology can also solve the problem of poor communication caused by regional dialects. Online editing technology can be used to assist the financing request object to supplement the materials required for due diligence online. Specifically, the content filled in by the financing request object can be identified through preset field rules. The preset field rules can also be used to perform real-time verification of the content filled in by the financing request object and provide feedback on the error fields.

[0067] Next, in operation S250, the credit limit associated with the financing request object is determined based on the acquired registration data, and the credit limit is returned to the bank financing platform so that the bank financing platform can perform a lending operation based on the credit limit.

[0068] In this embodiment, specifically, before calculating the credit limit, the on-site record data obtained by the risk control personnel through on-site due diligence can be received, and then the difference measurement value between the registration data and the on-site record data can be determined according to the preset data weight and scaling factor. When the difference measurement value is lower than the preset threshold, the operation of determining the credit limit is performed; when the difference measurement value is higher than the preset threshold, the online due diligence is stopped, and the credit business request of the financing request object is rejected.

[0069] In order to prevent the object of financing request from uploading false data, the authenticity of the acquired registration data can be verified by using part of the on-site due diligence data. When calculating the difference measurement value between the registration data and the on-site recorded data, the difference between the two data can be measured according to the preset data weight and scaling factor for the data to be verified. The data weight indicates the importance of the data to be verified. The larger the data weight, the higher the importance of the data to be verified. The data weight can be set according to the actual due diligence needs. Exemplarily, the operating flow has a very important reference value for evaluating the repayment ability of the object of financing request. Therefore, a higher data weight can be set for the data of operating flow. The scaling factor describes the maximum difference allowed between the registration data and the real data. Exemplarily, for small customers, the preset data weight of the operating flow is 0.8, and the scaling factor is 5%. When the registered operating flow of the object of financing request is 100,000 yuan and its actual operating flow is 80,000 yuan, the difference measurement value between the registered operating flow and the actual operating flow can be determined as 0.8×[10×(1-5%)-8]=1.2 (10,000 yuan).

[0070] When the difference measurement value between the registration data and the on-site record data is lower than the preset threshold, the business logic verification can be performed on the financing request object based on the obtained registration data. The business logic verification can specifically include verifying whether the business scale of the financing request object meets the upper limit requirements, whether the enterprise registration place corresponds to specific business switch information, whether the product type meets the preset business requirements, etc. If the business logic verification passes, the operation of determining the credit limit is executed; if the business logic verification fails, the credit business request of the financing request object is rejected, and the online due diligence process for the financing request object is terminated.

[0071] When the business logic verification passes, the registration data of the financing request object is counted according to the specified dimension to evaluate the repayment ability and predict the lending risk of the financing request object. At the same time, the credit limit for the financing request object can be determined by combining the number of tag matching items, the number of projects to be adjusted, and the different judgment criteria for repayment ability, business qualifications, loan purposes, etc. in specific industries or regions. After the credit limit is determined, the credit limit will be returned to the bank financing platform for the bank financing platform to use the credit limit as a reference to perform lending operations on the financing request object.

[0072] Figure 4 The following schematically shows a schematic diagram of an online due diligence processing system according to an embodiment of the present disclosure. Figure 4 As shown, the system 400 may include an interaction module, a business processing module, a parameter configuration module and a data model module, and each module cooperates with each other to realize the online processing of the credit business due diligence process.

[0073] Figure 5 A schematic diagram of information processing of an interactive module according to an embodiment of the present disclosure is shown schematically. Figure 5 As shown, in the processing process 500, the financing request object logs in to the interactive module through the designated channel at the designated time. The interactive module provides image transmission, image recognition, voice recognition, online editing and other functions to realize the online transmission of the customer information of the financing request object to the risk control personnel. The risk control personnel verifies the customer information and determines whether additional materials are required. If so, they select the type and template of the required additional materials and use the interactive module to display the relevant content so that the financing request object can complete the customer information according to the displayed content. When it is confirmed that no additional materials are required and the materials are confirmed to be authentic, the online due diligence begins.

[0074] Figure 6 A schematic diagram of information processing of a business processing module according to an embodiment of the present disclosure is shown schematically. Figure 6 As shown, in the processing 600, after receiving the customer information of the object of the financing request, the interaction module passes the customer information to the data model module, so that the data model module can perform risk quantification scoring based on the customer information to obtain the screening results. The business processing module determines whether to conduct online due diligence based on the screening results. If so, the data model module performs label matching, and determines the target due diligence model applicable to the object of the financing request based on the label matching results. Then, the business processing module conducts online due diligence based on the target due diligence model, and after the online due diligence is completed, continues to conduct offline due diligence until the due diligence is completed. When it is determined not to conduct online due diligence, the business processing module directly conducts offline due diligence until the due diligence is completed.

[0075] Figure 7A schematic diagram of information processing of a data model module according to an embodiment of the present disclosure is shown schematically. Figure 7 As shown, in the processing 700, the parameter configuration module generates a risk quantification label based on the customer information received by the interaction module. The data model module performs risk quantification scoring based on the risk quantification label to obtain the screening result. The business processing module determines whether to conduct online due diligence based on the screening result, and if so, performs label matching through the data model module, and determines the target due diligence model applicable to the financing request object based on the label matching result. The parameter configuration module generates a personalized document file based on the target due diligence model, and returns the personalized document file to the financing request object through the interaction module to initiate the online due diligence process.

[0076] Figure 8 A schematic diagram of information processing of a parameter configuration module according to an embodiment of the present disclosure is shown schematically. Figure 8 As shown, in the processing 800, the parameter configuration module generates a risk quantification tag based on the customer information received by the interaction module. The risk quantification tag is used to assist in evaluating the risk quantification score of the financing request object and obtain the screening result. The business processing module determines whether to conduct online due diligence based on the screening result. If so, after determining the target due diligence model suitable for the financing request object, the parameter configuration module configures the filling template and generates a personalized document file. The parameter configuration module returns the personalized document file to the financing request object through the interaction module to initiate the online due diligence process.

[0077] Fig. 9 A block diagram of an online due diligence processing device according to an embodiment of the present disclosure is schematically shown.

[0078] like Fig. 9 As shown, the apparatus 900 includes an acquisition module 901 , a first processing module 902 , a second processing module 903 , a third processing module 904 and a fourth processing module 905 .

[0079] Specifically, the acquisition module 901 is used to obtain the preset type risk characterization information of the financing request object; the first processing module 902 is used to determine at least one risk quantification label associated with the financing request object based on the risk characterization information; the second processing module 903 is used to determine the set of pending projects applicable to the financing request object according to the at least one risk quantification label; the third processing module 904 is used to return the set of pending projects to the financing request object, so that the financing request object uploads registration data based on the set of pending projects; the fourth processing module 905 is used to determine the credit line associated with the financing request object according to the acquired registration data, and return the credit line to the bank financing platform, so that the bank financing platform can perform lending operations based on the credit line.

[0080] In the disclosed embodiment, the preset risk characterization information of the financing request object is obtained; based on the risk characterization information, at least one risk quantification label associated with the financing request object is determined; according to the at least one risk quantification label, a set of projects to be adjusted applicable to the financing request object is determined; the set of projects to be adjusted is returned to the financing request object, so that the financing request object uploads registration data based on the set of projects to be adjusted; according to the obtained registration data, the credit line associated with the financing request object is determined, and the credit line is returned to the bank financing platform, so that the bank financing platform can perform a lending operation based on the credit line. By determining at least one risk quantification label associated with the financing request object, and determining the set of projects to be adjusted applicable to the financing request object based on the at least one risk quantification label, so that the financing request object uploads registration data online based on the set of projects to be adjusted, it can be achieved that while providing an effective risk reference basis for the bank financing platform, the labor cost consumption of the risk control personnel for offline due diligence can be effectively reduced, and the workload of offline credit line evaluation can be effectively reduced, which is conducive to effectively improving the due diligence efficiency of small and micro financing business, and effectively improving the convenience of due diligence of credit risk control, and can fully meet the requirements of the rapid development of online small and micro financing business.

[0081] As a feasible embodiment, the second processing module includes: a first processing sub-module, used to determine the target due diligence model with the highest matching degree with at least one risk quantification label, the target due diligence model is preset with at least one risk reference label, and the matching degree between at least one risk reference label and at least one risk quantification label is the highest; a second processing sub-module, used to use the set of projects to be adjusted associated with the target due diligence model as the set of projects to be adjusted suitable for the financing request object.

[0082] As a feasible embodiment, the third processing module includes: a third processing sub-module, used to generate a personalized document file according to the set of items to be adjusted; a fourth processing sub-module, used to return the personalized document file to the financing request object, so that the financing request object uploads registration data according to the personalized document file; wherein, the method of uploading registration data includes at least one of the following: uploading registration data using image transmission technology; uploading registration data using image recognition technology; uploading registration data using voice recognition technology; uploading registration data using online editing technology.

[0083] As a feasible embodiment, the device also includes: a fifth processing module, which is used to determine the risk estimation score of the financing request object based on the risk characterization information; obtain risk estimation reference data associated with the financing request object from a preset data source; adjust the risk estimation score according to the risk estimation reference data to obtain a risk quantification score of the financing request object; and generate an online due diligence task for the financing request object when the risk quantification score is lower than a preset threshold.

[0084] As a feasible embodiment, the fourth processing module includes: a fifth processing sub-module, used to receive on-site record data obtained by risk control personnel through on-site due diligence; determine the difference measurement value between the registration data and the on-site record data based on preset data weights and scaling factors; and when the difference measurement value is lower than a preset threshold, execute the operation of determining the credit limit.

[0085] As a feasible embodiment, the fourth processing module also includes: a sixth processing sub-module, which is used to perform a business logic check on the financing request object according to the acquired registration data; and when the business logic check passes, determine the credit limit based on the registration data.

[0086] As a feasible embodiment, the fifth processing module is further used to perform a blacklist check on the financing request object; and when the financing request object is not on the preset blacklist, perform an operation of determining a risk estimation score.

[0087] As a feasible embodiment, the risk characterization information includes at least one of the following: enterprise entity information, financial account information, company product information, usage and priority, and policy support content.

[0088] It should be noted that in the embodiments of the present disclosure, the implementation of the device part is the same as or similar to the implementation of the method part, and will not be repeated here.

[0089] According to any one or more of the modules of the embodiments of the present disclosure, or at least part of the functions of any one of them, can be implemented in one module. According to any one or more of the modules of the embodiments of the present disclosure, it can be split into multiple modules for implementation. According to any one or more of the modules of the embodiments of the present disclosure, it 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 of 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 any appropriate combination of any of them. Or according to one or more of the modules of the embodiments of the present disclosure, it can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be performed.

[0090] For example, any multiple of the acquisition module 901, the first processing module 902, the second processing module 903, the third processing module 904, and the fourth processing module 905 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 acquisition module 901, the first processing module 902, the second processing module 903, the third processing module 904, and the fourth processing module 905 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 by any one of the three implementation methods of software, hardware, and firmware, or by a suitable combination of any of them. At least one of the acquisition module 901 , the first processing module 902 , the second processing module 903 , the third processing module 904 and the fourth processing module 905 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be executed.

[0091] Fig.10 A block diagram of an electronic device according to an embodiment of the present disclosure is schematically shown. Fig.10 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0092] like Fig.10 As shown, the electronic device 1000 includes a processor 1010 and a computer-readable storage medium 1020. The electronic device 1000 can execute the method according to the embodiment of the present disclosure.

[0093] Specifically, the processor 1010 may include, for example, a general-purpose microprocessor, 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 1010 may also include an onboard memory for cache purposes. The processor 1010 may be a single processing module or multiple processing modules for executing different actions of the method flow according to the embodiment of the present disclosure.

[0094] The computer-readable storage medium 1020 may be, for example, a non-volatile computer-readable storage medium, and specific examples include but are not limited to: a magnetic storage device, such as a magnetic tape or a hard disk (HDD); an optical storage device, such as a compact disk (CD-ROM); a memory, such as a random access memory (RAM) or a flash memory; and the like.

[0095] The computer-readable storage medium 1020 may include a computer program 1021 , which may include code / computer-executable instructions that, when executed by the processor 1010 , cause the processor 1010 to perform a method according to an embodiment of the present disclosure or any variation thereof.

[0096] The computer program 1021 may be configured to have, for example, a computer program code including a computer program module. For example, in an exemplary embodiment, the code in the computer program 1021 may include one or more program modules, for example, including 1021A, module 1021B, ... It should be noted that the division method and number of modules are not fixed, and those skilled in the art may use appropriate program modules or program module combinations according to actual conditions, and when these program module combinations are executed by the processor 1010, the processor 1010 may execute the method according to the embodiment of the present disclosure or any variation thereof.

[0097] According to an embodiment of the present disclosure, at least one of the acquisition module 901, the first processing module 902, the second processing module 903, the third processing module 904, and the fourth processing module 905 can be implemented as a reference. Fig.10 The computer program modules described herein, when executed by the processor 1010, can implement the corresponding operations described above.

[0098] 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.

[0099] 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.

Claims

1. An online due diligence processing method, comprising: Obtaining risk characterization information of preset categories of financing request objects; Based on the risk characterization information, determining at least one risk quantification tag associated with the financing request object; Determining a set of pending projects applicable to the financing request object according to the at least one risk quantification tag; Returning the set of items to be adjusted to the financing request object, so that the financing request object uploads registration data based on the set of items to be adjusted; Determine the credit limit associated with the financing request object according to the acquired registration data, and return the credit limit to the bank financing platform so that the bank financing platform can perform a lending operation based on the credit limit; The step of determining the set of pending projects applicable to the financing request object according to the at least one risk quantification label includes: Determining a target due diligence model that has the highest degree of match with the at least one risk quantification label, wherein the target due diligence model is preset with at least one risk reference label, and the at least one risk reference label has the highest degree of match with the at least one risk quantification label; and The set of projects to be adjusted associated with the target due diligence model is used as the set of projects to be adjusted applicable to the financing request object; Before determining at least one risk quantification tag associated with the financing request object based on the risk characterization information, the method further includes: Determining a risk estimation score of the financing request object based on the risk characterization information; Acquire risk estimation reference data associated with the financing request object from a preset data source; According to the risk estimation reference data, adjusting the risk estimation score to obtain a risk quantification score of the financing request object; and When the risk quantification score is lower than a preset threshold, an online due diligence task is generated for the financing request object.

2. The method according to claim 1, wherein: The step of returning the set of items to be adjusted to the financing request object so that the financing request object uploads registration data based on the set of items to be adjusted includes: Generate a personalized document file according to the set of items to be adjusted; Returning the personalized document file to the financing request object, so that the financing request object uploads the registration data according to the personalized document file; The method of uploading the registration data includes at least one of the following: Uploading the registration data using image transmission technology; Uploading the registration data using image recognition technology; Uploading the registration data using voice recognition technology; The registration data is uploaded using online editing technology.

3. The method according to any one of claims 1 or 2, wherein: Before determining the credit limit associated with the financing request object according to the acquired registration data, the method further includes: Receive on-site record data obtained by risk control personnel through on-site due diligence; determining a difference measure between the registration data and the field recorded data according to a preset data weight and a scaling factor; and In the case where the difference measurement value is lower than a preset threshold, an operation of determining the credit limit is performed.

4. The method according to claim 3, wherein: When the difference measurement value is lower than a preset threshold, performing the operation of determining the credit limit includes: Performing a business logic check on the financing request object based on the acquired registration data; and When the business logic verification passes, the credit limit is determined based on the registration data.

5. The method according to claim 1, wherein: Before determining the risk estimation score of the financing request object based on the risk characterization information, the method further includes: Conduct a blacklist check on the object of the financing request; and In a case where the financing request object is not in a preset blacklist, an operation of determining the risk estimation score is performed.

6. The method according to claim 1, wherein: The risk characterization information includes at least one of the following: Enterprise entity information, financial account information, company product information, usage and priority, and policy support content.

7. An online due diligence processing device, comprising: An acquisition module, used to acquire risk characterization information of a preset type of financing request object; A first processing module, configured to determine at least one risk quantification tag associated with the financing request object based on the risk characterization information; A second processing module is used to determine a set of pending projects applicable to the financing request object according to the at least one risk quantification label; A third processing module is used to return the set of projects to be adjusted to the financing request object, so that the financing request object uploads registration data based on the set of projects to be adjusted; A fourth processing module, configured to determine a credit limit associated with the financing request object according to the acquired registration data, and return the credit limit to the bank financing platform, so that the bank financing platform can perform a lending operation based on the credit limit; A fifth processing module, configured to determine a risk estimation score of the financing request object based on the risk characterization information; Acquire risk estimation reference data associated with the financing request object from a preset data source; According to the risk estimation reference data, an adjustment process is performed on the risk estimation score to obtain a risk quantification score of the financing request object; and generating an online due diligence task for the financing request object when the risk quantification score is lower than a preset threshold; Among them, the second processing module includes: a first processing sub-module, used to determine the target due diligence model with the highest matching degree with the at least one risk quantification label, the target due diligence model is preset with at least one risk reference label, and the matching degree between the at least one risk reference label and the at least one risk quantification label is the highest; a second processing sub-module, used to use the set of projects to be adjusted associated with the target due diligence model as the set of projects to be adjusted applicable to the financing request object.

8. An electronic device comprising: one or more processors; as well as a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program or instructions, which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 6.

Images