A method, system, electronic device, and storage medium for predicting loan overdue risks

Abstract

The present invention relates to the field of Internet finance technology, and in particular to a method, system, electronic device and storage medium for predicting the risk of loan overdue. The method includes collecting abnormal information of users at a preset collection frequency to determine the current risk level; matching a corresponding inquiry strategy according to the current risk level; receiving response information fed back by the user based on the inquiry strategy; comparing the response information with preset response information to obtain the response accuracy rate; updating the current risk level according to the response accuracy rate; and cyclically executing the above steps based on the updated risk level. By monitoring the information of the loaned users and analyzing the user information, the above method predicts whether the user has an overdue risk and determines the risk level, and takes corresponding measures for the user according to the risk level, which can reduce the overdue behavior of users caused by objective factors.

Description

Technical Field

[0001] The present invention relates to the field of Internet finance technology, and in particular, to a method, system, electronic device, and storage medium for predicting loan overdue risks. Background Art

[0002] With the development of financial electronic services, financial institutions have launched various mobile loan software, enabling users to handle loan services more conveniently and quickly. However, due to problems such as slow capital repayment, job changes, forgetfulness, and credit of borrowers, there have also been many overdue phenomena, and various collection methods have emerged accordingly.

[0003] Regarding the overdue phenomenon, there are also many objective and controllable factors for borrowers. Monitoring their information and predicting the overdue risk after the borrowers borrow money and taking measures in advance according to the overdue risk will greatly reduce the overdue phenomenon of borrowers. The inventor of the present invention found that most of the preventive measures in the related technologies only adopt the method of manual outbound calls, and by adopting such a method, the prediction of loan overdue risks is not accurate enough. Summary of the Invention

[0004] In view of the current situation that there are more and more loan overdue phenomena and the prediction of loan overdue risks is not accurate enough, the present application provides a method, system, electronic device, and storage medium for predicting loan overdue risks, which monitors the users who have already taken loans and makes a relatively accurate prediction of the overdue risks of the users.

[0005] The above application objectives of the present application are achieved through the following technical solutions:

[0006] In a first aspect, the present application provides a method for predicting loan overdue risks, and the method includes:

[0007] Risk level determination step: Collect the abnormal information of the user according to a preset collection frequency, and determine the current risk level; the current risk level is divided according to the quantity of the abnormal information;

[0008] Inquiry strategy determination step: Match the corresponding inquiry strategy according to the current risk level;

[0009] Response information acquisition step: Receive the response information fed back by the user based on the inquiry strategy;

[0010] Response information comparison step: Compare the response information with the preset response information to obtain the response correct rate;

[0011] Risk level update step: Update the current risk level according to the response correct rate;

[0012] Based on the updated risk level, the inquiry strategy determination step, the response information acquisition step, the response information comparison step, and the risk level update step are cyclically executed.

[0013] By collecting information of loaned users, analyzing abnormal information in the user information to determine whether the user has overdue risks, monitoring the user's behavior to predict in advance whether the user may have overdue repayments, analyzing the overdue risk level of the user according to the number of abnormal information of the user, matching corresponding inquiry strategies for the user, and making information investigations and prompts according to the inquiry strategies, it is possible to greatly reduce the overdue repayment behavior of users caused by objective factors. And matching different inquiries for different risk levels can enhance the inquiry effect in different scenarios and increase the possibility of users' active repayment.

[0014] Optionally, the abnormal information includes abnormal information of extended information, abnormal repayment information of the user, and response information of the user below the preset response correct rate.

[0015] Optionally, the inquiry strategies include questionnaires, intelligent robot outbound calls, and manual calls.

[0016] Optionally, the risk level is divided according to the number of the abnormal information, specifically: when the number of abnormal information is 0, the current risk level of the user is normal; when the number of abnormal information is 1, the current risk level of the user is low risk; when the number of abnormal information is 2, the current risk level of the user is medium risk; when the number of abnormal information is 3, the current risk level of the user is high risk.

[0017] Optionally, the specific steps for determining the inquiry strategy are: when the current risk level is low risk, send a questionnaire to the user terminal; when the current risk level is medium risk, match an intelligent outbound call robot to call; when the current risk level is high risk, match a manual call;

[0018] The inquiry questions of the questionnaire, the outbound call robot, and the manual call match corresponding questions in the question database according to the abnormal information of the user.

[0019] Optionally, the specific steps for comparing the response information are: extracting keywords from the received response information; comparing the keywords with the preset keywords, and obtaining the response correct rate according to the proportion of the number of successfully compared keywords in the total number of extracted keywords.

[0020] Optionally, the specific steps for updating the risk level are: judging whether the response information is abnormal information according to the response information correct rate; if so, increasing the number of abnormal information by 1; updating the current risk level of the user according to the current number of abnormal information.

[0021] In a second aspect, the present application provides a loan overdue risk level prediction system, which includes:

[0022] A risk level determination module, which includes a collection unit and a judgment unit. The collection unit collects the abnormal information of the user according to a preset collection frequency, and the judgment unit determines the current risk level based on the number of current abnormal information collected by the collection unit;

[0023] An inquiry strategy determination module, which matches the corresponding inquiry strategy according to the current risk level;

[0024] A response information acquisition module, which receives the response information fed back by the user based on the inquiry strategy;

[0025] A response information comparison module, which compares the response information with the preset response information to obtain the response accuracy rate, and determines whether the response information is abnormal information according to the response accuracy rate;

[0026] A risk level update module, which feeds back the response information to the collection unit and updates the current risk level according to the response information.

[0027] Thirdly, the present application provides an electronic device, which includes a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the method described in any one of the above.

[0028] Fourthly, the present application provides a computer-readable medium, on which a computer program is stored, wherein the computer program is configured to execute the method described in any one of the above when running.

[0029] In summary, the present application has the following beneficial effects:

[0030] 1. Analyze the abnormal information in the user information to judge whether the user has an overdue risk, and can monitor the user's behavior to predict in advance whether the user may have an overdue repayment;

[0031] 2. Analyze the overdue risk level of the user by the number of the user's abnormal information, and match the corresponding inquiry method to the user for information investigation and prompt, which can greatly reduce the overdue repayment behavior of the user caused by objective factors;

[0032] 3. Matching different inquiry methods for different risk levels can enhance the inquiry effect in different scenarios and increase the possibility of the user's active repayment. Description of the Drawings

[0033] Combined with the drawings and referring to the following detailed description, the above and other features, advantages and aspects of the embodiments of the present application will become more obvious. In the drawings, the same or similar reference numerals represent the same or similar elements, where:

[0034] Figure 1 is a flowchart of a loan overdue risk prediction method according to an embodiment of the present application.

[0035] Figure 2 It is a structural block diagram of a loan overdue risk prediction system according to an embodiment of the present application.

[0036] Figure 3 It is a flowchart of a loan overdue risk prediction method according to an optional embodiment of the present application.

[0037] Figure 4 It is a schematic structural diagram of a terminal device or a server for implementing an embodiment of the present application.

[0038] Figure 5 It is a schematic structural diagram of an electronic device provided. Detailed implementation manners

[0039] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

[0040] The system architecture involved in the embodiments of the present application will be introduced below. It should be noted that the system architecture and business scenarios described in the embodiments of the present application are for more clearly explaining the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those of ordinary skill in the art can know that with the evolution of the network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0041] A loan overdue risk prediction method provided by an embodiment of the present application can be applied to a server. The server interacts with a client to complete the determination of the overdue risk level of a user after borrowing. In the embodiment of the present application, user information is collected to monitor the user, abnormal information in the user information is analyzed, the overdue risk level of the user is judged, corresponding inquiry strategies are adopted according to the user risk level, the user risk level is updated again according to the response situation of the user, and relevant measures are taken according to the updated risk level of the user. Through the above methods, the user behavior can be monitored to predict in advance whether the user is likely to have an overdue repayment. By adopting corresponding inquiries for the user, the inquiry effect in different scenarios can be enhanced, the overdue repayment behavior of the user caused by objective factors can be reduced, and the possibility of the user's active repayment can be improved.

[0042] Such as Figure 1 It is a flowchart of a loan overdue risk prediction method according to an embodiment of the present invention. The process includes the following steps:

[0043] S101, a risk level determination step, collecting abnormal information of a user at a preset collection frequency and determining the current risk level.

[0044] Before collecting the user's abnormal information, it also includes obtaining the user information, which includes the basic information when the user applies for a loan, the extended information obtained based on the basic information, the user's repayment information, and the user's response information. Among them, the basic information belongs to static information, and the extended information, the user's repayment information, and the user's response information all belong to dynamic information. Specifically, the basic information is the information such as the name, contact information, ID number, associated enterprise, etc. entered by the user when submitting a loan application on the client side; the extended information is the information such as the user's other loan situations, work status (employed, unemployed, etc.), the names and phone numbers of associated persons, etc. obtained through the user's basic information, which needs to be updated regularly; the user's repayment information is the repayment time and repayment situation of the user every month or quarter; the user's response information is the response information obtained from the user's responses to different inquiry methods.

[0045] Collect information according to the preset collection frequency, which can be set according to quarters, months, days, hours, minutes, etc. In the embodiments of this application, the collection frequency of the extended information is set to be collected and updated once every 7 working days; the collection frequency of the user's repayment information is updated according to the user's repayment cycle. If the user repays according to the monthly repayment frequency, it is set to collect and update the user's repayment information on the monthly due date; the collection and update time of the user's response information is to collect the response information of the user to the corresponding inquiry method after making an inquiry to the user.

[0046] In the embodiments of this application, the collection frequency of the user information, on the one hand, is collected according to the cycle of abnormal information appearing in different information, so as to update the abnormal information in time; on the other hand, setting a reasonable collection frequency will not excessively occupy server resources.

[0047] In the embodiments of this application, the abnormal information includes the abnormal information of the extended information, the user's abnormal repayment information, and the response information of the user below the preset response accuracy rate; the abnormal information of the extended information is that abnormal behavior is found when updating the extended information, then this extended information is recorded as an abnormal information. The abnormal behavior in the extended information is determined by comparing with the preset abnormal behavior, which can be behaviors such as the user being unemployed, other loans being overdue, or the enterprise being cancelled, etc.; the user's abnormal repayment information is that abnormal behavior is found when updating the user's repayment information, then this user's repayment information is recorded as an abnormal information. The user's abnormal repayment behavior includes behaviors such as the user delaying the repayment date and installment payment of the amount, etc.; the response information of the user below the preset response accuracy rate is to obtain the response information of the user after different inquiry methods, and the accuracy rate is obtained through comparison and analysis. The response information below the preset response accuracy rate can be set to be recorded as abnormal information when the score is lower than 80%.

[0048] Determine the current risk level of the user according to the number of abnormal information collected. In this embodiment, when the number of abnormal information is 0, the current risk level of the user is normal; when the number of abnormal information is 1, the current risk level of the user is low risk; when the number of abnormal information is 2, the current risk level of the user is medium risk; when the number of abnormal information is 3, the current risk level of the user is high risk.

[0049] S102, inquiry strategy determination step, match the corresponding inquiry strategy according to the current risk level.

[0050] In the embodiment of the present application, receive the current risk level of the user output by step S101. When the current risk level of the user is low risk, send a questionnaire to the user terminal to inquire about the user; when the current risk level of the user is medium risk, match the intelligent outbound robot call method to inquire about the user; when the current risk level of the user is high risk, match the manual call method to inquire about the user.

[0051] In the embodiment of the present application, the inquiry questions of the questionnaire, the outbound robot, and the manual call are intelligently matched with the corresponding inquiry questions in the question database according to the user's abnormal information. Specifically, extract keywords from the abnormal information and match the questions in the question database according to the matching repetition degree.

[0052] In an example, show a scenario of matching questions: If the abnormal information of the user is "The company has undergone a change of legal person." that appears in the expansion information, the extracted keywords are "company" and "change of legal person", and the coincidence degree with "Has your company undergone a change of legal person?" in the question bank is the highest, then match this question as the inquiry question.

[0053] S103, response information acquisition step, receive the response information fed back by the user based on the inquiry strategy.

[0054] In the embodiment of the present application, if it is the inquiry method of the questionnaire, receive the questionnaire returned by the user; if it is the inquiry method of the intelligent outbound call, identify the voice information received by the intelligent outbound robot; if it is the inquiry method of the manual call, receive the user response content manually input after the manual call.

[0055] S104, response information comparison step, compare the response information with the preset response information to obtain the response correct rate.

[0056] In the embodiment of the present application, extract multiple keywords from the user response information output in step S103; compare the multiple keywords with the preset keywords, and obtain the response correct rate according to the proportion of the number of successfully compared keywords in the total number of extracted keywords.

[0057] In an example, a scenario of question comparison is shown: By making an intelligent outbound call to ask the user questions, such as "Has your company undergone a change of legal representative?", the preset keyword in the server is "Yes"; the response information of the user is "There has been no change of legal representative", then the extracted keyword is "No", and the keyword comparison fails.

[0058] In an example, the response accuracy rate is obtained by calculating the proportion of the number of successfully compared keywords in the total number of extracted keywords: By conducting a questionnaire to ask the user questions, there are 10 questions listed in the questionnaire, and the user side can only select or enter "Yes" or "No". Based on the 10 questions proposed, in the order of question numbers, the preset keywords are "Yes" or "No"; in the response information fed back by the user, the server obtains 10 keywords and compares them with the preset keywords of the corresponding questions to obtain the number of successfully compared keywords. For example, the number of successfully compared keywords is 8; then, based on the formula: response accuracy rate (%) = number of successfully compared keywords / total number of keywords, that is, the response accuracy rate is: (8 / 10) * 100% = 80%.

[0059] S105, the risk level update step, updates the current risk level according to the response accuracy rate.

[0060] In the embodiment of the present application, before step S105, it also includes analyzing whether the response information is abnormal information. If the response accuracy rate is lower than the preset response accuracy rate, in this embodiment, it can be set that when the accuracy rate is lower than 80%, this response information is recorded as abnormal information.

[0061] If the response accuracy rate is higher than 80%, then the user's response information this time is normal information, the number of abnormal information remains unchanged, and the user's risk level remains unchanged.

[0062] If the response accuracy rate is lower than 80%, then the number of abnormal information is incremented by 1, and the current risk level is updated according to the updated number of abnormal information.

[0063] In an example, a scenario where the abnormal information changes is shown: If the number of abnormal information of the user before being questioned is 1, and the corresponding risk level is low risk, after questioning the user in the form of a corresponding questionnaire, the response accuracy rate of the user is lower than 80%, then the number of abnormal information of the user becomes 2, and the corresponding risk level becomes medium risk.

[0064] In an example, a scenario where the abnormal information does not change is shown: If the number of abnormal information of the user before being questioned is 1, and the corresponding risk level is low risk, after questioning the user in the form of a corresponding questionnaire, the response accuracy rate of the user is higher than 80%, then the number of abnormal information of the user remains 1, and the corresponding risk level remains low risk.

[0065] After step S105, if the current risk level changes after the update, continue to execute the inquiry strategy determination step, the response information acquisition step, the response information comparison step, and the risk level update step to obtain the current risk level; if the current risk level remains unchanged after the update, temporarily do not execute other steps until the number of abnormal information in the risk level determination step changes and the risk level changes, then continue to execute the inquiry strategy determination step, the response information acquisition step, the response information comparison step, and the risk level update step; in this embodiment, it is set that when the current risk level of the user appears as high risk twice, stop monitoring this user and take measures to stop lending to this user.

[0066] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0067] The above is the introduction of the method embodiments. The following further illustrates the solution of this application through device embodiments.

[0068] Figure 2 is a structural block diagram of a loan overdue risk prediction system according to an embodiment of the present invention, as Figure 2 shown, including:

[0069] A risk level determination module 10, the risk level determination module includes a collection unit 101 and a judgment unit 102. The collection unit 101 is used to collect user information according to a preset collection frequency and collect abnormal information of the user in the user information. The judgment unit 102 judges the current risk level according to the number of abnormal information collected by the collection unit 101.

[0070] An inquiry strategy determination module 20, which matches a corresponding inquiry strategy according to the current risk level.

[0071] A response information acquisition module 30, which receives the response information fed back by the user based on the inquiry strategy.

[0072] A response information comparison module 40, which compares the response information with preset response information to obtain a response accuracy rate, and judges whether the response information is abnormal information according to the response accuracy rate.

[0073] A risk level update module 50, which feeds the response information back to the collection unit 101 and updates the current risk level according to the response information.

[0074] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the described modules can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0075] To facilitate the understanding of the technical solutions provided by the present invention, the following will be described in detail in combination with the embodiments of specific scenarios.

[0076] As Figure 3 shown, the embodiments of the present application are directed to monitoring the information of loaned users, judging the loan overdue risk of users according to the number of abnormal information of users, and implementing corresponding inquiry methods for them.

[0077] For loaned users, the acquisition unit first obtains user information, which includes static information and dynamic information.

[0078] The static information is basic information, such as the name, contact information, ID number, etc. input by the user when submitting a loan application.

[0079] The dynamic information includes extended information, user repayment information, and user response information. The collection frequency of the extended information is set to be collected and updated once every 7 working days; the collection frequency of the user repayment information is updated according to the user's due repayment cycle. If the user repays according to the monthly repayment frequency, the user repayment information is set to be collected and updated on the monthly due repayment date; the collection and update time of the user response information is after making an inquiry to the user, and the response information made by the user to the corresponding inquiry method is collected.

[0080] Abnormal information is collected from the obtained user information, including abnormal information of extended information, abnormal user repayment information, and response information of the user below the preset response accuracy rate; the abnormal information of extended information is the discovery of abnormal behavior when updating the extended information, which can be the occurrence of unemployment, overdue of other loans, or enterprise cancellation in this extended information, then this extended information is recorded as an abnormal information; the abnormal user repayment information is the discovery of abnormal behavior when updating the user repayment information, such as the delay of the user's monthly repayment date, installment of the amount, etc., then this user repayment information is recorded as an abnormal information; the response information of the user below the preset response accuracy rate is the response information obtained by the user after different inquiry methods, and the accuracy rate is obtained through comparison and analysis. The response information below 80% of the preset response accuracy rate is recorded as an abnormal information.

[0081] The judgment unit obtains the user information sent by the acquisition unit, determines the number of abnormal information in the user information, and judges the current risk level according to the number of abnormal information.

[0082] When the number of exception messages is 0, the user's current risk level is normal; when the number of exception messages is 1, the user's current risk level is low risk; when the number of exception messages is 2, the user's current risk level is medium risk; when the number of exception messages is 3, the user's current risk level is high risk.

[0083] The inquiry strategy determination module receives the updated current risk level of the judgment unit, and matches the corresponding inquiry method according to the current risk level. When the user's current risk level is low risk, a questionnaire is sent to the user side to inquire about the user; when the user's current risk level is medium risk, an intelligent outbound robot call method is matched to inquire about the user; when the user's current risk level is high risk, a manual call method is matched to inquire about the user.

[0084] Set the number of times of receiving the high-risk level. For example, when the high-risk level is received for the second time, the monitoring of this user is stopped and the user information is output to the list of overdue loan collection.

[0085] In an example, a scenario of matching the inquiry strategy is shown: if the user's current risk level is low risk, a questionnaire is sent to this user for inquiry. The questionnaire matches the corresponding questions according to the exception information of the user. For example, if the content of the user's exception information is that other loan software in the extended information has an overdue behavior, questions are matched for its overdue behavior.

[0086] The response information acquisition module receives the responses of the user to different inquiry methods. If it is a questionnaire, it receives the questionnaire response information sent by the user; if it is an intelligent outbound inquiry method, it identifies the voice information received by the intelligent outbound robot; if it is a manual call inquiry method, it receives the user response content manually input after the manual call. The response information comparison module extracts keywords from the response information obtained by the response information acquisition module, compares the keywords with the preset keywords, and obtains the response correct rate according to the proportion of the number of successfully compared keywords in the total number of extracted keywords. When the correct rate is set to be less than 80%, this response information is marked as exception information.

[0087] The risk level update module feeds back the response information analyzed by the response information comparison module to the acquisition unit. If the current response information is abnormal information, the current risk level changes and the inquiry strategy determination module, the response information acquisition module, the response information comparison module, and the risk level update module continue to run; if the current response information is not abnormal information, the risk level determination module continues to run. When the current risk level changes, the inquiry strategy determination module, the response information acquisition module, the response information comparison module, and the risk level update module continue to run; in the above steps, when the inquiry strategy determination module receives two high risk levels, the monitoring of this user is stopped, and measures to stop lending are taken against this user.

[0088] Figure 4 FIG. shows a schematic structural diagram of a terminal device or a server suitable for implementing an embodiment of the present application, such as Figure 4 shown, the terminal device or the server includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage section into a random access memory (RAM) 403. In the RAM 403, various programs and data required for system operation are also stored. The CPU 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0089] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as required. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as required, so that a computer program read from it can be installed into the storage section 408 as required.

[0090] Specifically, according to an embodiment of the present application, the above reference flow chart Figure 1The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a machine-readable medium, and the computer program includes program code for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the above functions defined in the system of the present application are executed.

[0091] It should be noted that the computer-readable medium shown in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. And in the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0092] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, and the foregoing module, segment of a program, or part of code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0093] The units or modules involved in the embodiments described in the present application can be implemented in software or in hardware. The described units or modules can also be provided in a processor. For example, it can be described as: A processor includes a risk level determination module, an inquiry strategy determination module, a response information acquisition module, a response information comparison module, a risk level update module, and a loop execution module. Among them, the names of these units or modules do not, in some cases, constitute a limitation on the units or modules themselves. For example, the risk level determination module can also be described as "a module for collecting abnormal information of a user according to a preset collection frequency and determining the current risk level".

[0094] As another aspect, the present application also provides a computer-readable storage medium, which may be included in the electronic device described in the foregoing embodiments; or may exist separately without being assembled into the electronic device. The foregoing computer-readable storage medium stores one or more programs, and when the foregoing programs are executed by one or more processors, they are used to perform the virtual object processing method described in the present application.

[0095] The above description is only for the preferred embodiments of the present application and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the application involved in the present application is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing application concept. For example, technical solutions formed by mutually replacing the above features with technical features having similar functions (but not limited to) claimed in the present application.

[0096] An electronic device is provided in the embodiments of the present application, such as Figure 5 shownFigure 5 The illustrated electronic device 500 includes: a processor 501 and a memory 503. Among them, the processor 501 and the memory 503 are connected, such as through a bus 502. Optionally, the electronic device 500 may further include a transceiver 504. It should be noted that in practical applications, the transceiver 504 is not limited to one, and the structure of the electronic device 500 does not constitute a limitation to the embodiments of the present application.

[0097] The processor 501 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in connection with the disclosure of the present application. The processor 501 may also be a combination that implements computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0098] The bus 502 may include a path for transmitting information between the above components. The bus 502 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 502 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5It is represented only by a thick line, but it does not mean that there is only one bus or one type of bus. The memory 503 can be a ROM (Read Only Memory), or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory), or other types of dynamic storage devices that can store information and instructions, or it can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0099] The memory 503 is used to store the application program code for executing the solution of this application, and is controlled by the processor 501 to execute. The processor 501 is used to execute the application program code stored in the memory 503 to implement the content shown in the foregoing method embodiments.

[0100] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is only an example and should not impose any restrictions on the functions and usage scope of the embodiments of this application.

[0101] The above is only the preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims

1. A method for predicting the risk of overdue loans, characterized in that, the method comprises the following steps: Risk level determination step: Collect abnormal information of users according to a preset collection frequency, and determine the current risk level; wherein, the current risk level is divided according to the quantity of the abnormal information; Inquiry strategy determination step: Match a corresponding inquiry strategy according to the current risk level; Response information acquisition step: Receive the response information fed back by the user based on the inquiry strategy; Response information comparison step: Compare the response information with preset response information to obtain the response accuracy rate; Risk level update step: Update the current risk level according to the response accuracy rate; Based on the updated current risk level, loop to execute the inquiry strategy determination step, the response information acquisition step, the response information comparison step and the risk level update step; if the current risk level remains unchanged after the update, other steps are not executed temporarily, until the quantity of abnormal information in the risk level determination step changes and the risk level changes, then continue to execute the inquiry strategy determination step, the response information acquisition step, the response information comparison step and the risk level update step.

2. The method for predicting the risk of overdue loans according to claim 1, characterized in that: The abnormal information includes abnormal information of extended information, abnormal repayment information of users, and response information of users with a response accuracy rate lower than the preset one.

3. The method for predicting the risk of overdue loans according to claim 1, characterized in that: The inquiry strategy includes one or several of sending a questionnaire for inquiry, making an outbound call by an intelligent robot for inquiry, and making an artificial call for inquiry.

4. The method for predicting the risk of overdue loans according to claim 3, characterized in that, the current risk level is divided according to the quantity of the abnormal information, specifically: When the quantity of the abnormal information is 0, the current risk level of the user is normal; When the quantity of the abnormal information is 1, the current risk level of the user is low risk; When the quantity of the abnormal information is 2, the current risk level of the user is medium risk; When the quantity of the abnormal information is 3, the current risk level of the user is high risk.

5. The method for predicting the risk of overdue loans according to claim 4, characterized in that, the inquiry strategy determination step is specifically: When the current risk level is low risk, send a questionnaire for inquiry to the user terminal; When the current risk level is medium risk, match an intelligent outbound robot for call inquiry; When the current risk level is high risk, match an artificial call for inquiry; The inquiry questions of the questionnaire for inquiry, the intelligent outbound robot inquiry and the artificial call inquiry are intelligently matched with corresponding questions in the question database according to the received abnormal information of the user.

6. The method for predicting the risk of overdue loans according to claim 1, characterized in that, the response information comparison step is specifically: Extract keywords from the received response information; Compare the keywords with preset keywords; Obtain the response accuracy rate according to the proportion of the number of successfully compared keywords in the total number of extracted keywords.

7. The method for predicting the risk of overdue loans according to claim 1, characterized in that, the risk level update step is specifically: Judge whether the response information is abnormal information according to the accuracy rate of the response information; If so, increase the number of abnormal information by 1; Update the current risk level of the user according to the current number of abnormal information.

8. A loan overdue risk prediction system, Characterized in that, Comprising: A risk level determination module, configured to collect abnormal information of a user according to a preset collection frequency and determine a current risk level; wherein, the current risk level is divided according to the number of the abnormal information; an inquiry strategy determination module, configured to match a corresponding inquiry strategy according to the current risk level; An inquiry strategy determination module, configured to match a corresponding inquiry strategy according to the current risk level; A response information acquisition module, configured to receive response information fed back by the user based on the inquiry strategy; A response information comparison module, configured to compare the response information with preset response information to obtain a response accuracy rate; A risk level update module, configured to update the current risk level according to the response accuracy rate; A loop execution module, configured to loop and execute inquiry strategy determination, response information acquisition, response information comparison, and risk level update based on the updated current risk level; if the current risk level remains unchanged after the update, other steps are not executed temporarily until the number of abnormal information in the risk level determination step changes and the risk level changes, and then continue to execute inquiry strategy determination, response information acquisition, response information comparison, and risk level update.

9. An electronic device, comprising a memory and a processor, Characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the method described in any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, Characterized in that, The program, when executed by a processor, implements the method described in any one of claims 1 to 7.

Images