Customer arrearage risk intelligent early warning method and system based on artificial intelligence
By using an AI-based method for early warning of overdue payments, the system dynamically calculates factors related to a customer's payment status, enabling personalized risk warnings. This addresses the issue of limited warning methods in existing technologies and enhances the customer experience.
Patent Information
- Application Number
- CN202511382515.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-25
- Publication Date
- 2025-12-30
AI Technical Summary
The existing overdue payment risk warning mechanism lacks in-depth analysis of customers' actual behavior and payment habits, resulting in a static and singular warning method that cannot be tailored to individuals. Customers are likely to ignore warning messages, leading to service interruptions.
By employing an AI-based approach, the system dynamically calculates representative payment status by acquiring customer status factors such as account balance, usage rate, usage duration, and billing price, and provides personalized risk warnings, including initial risk warnings and secondary risk warnings, thereby improving the alignment of warning plans with customer needs.
This effectively reduces the likelihood of customers ignoring warning messages, minimizes the risk of service interruption, and improves the customer experience.
Smart Images
Figure CN121235461A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of overdue risk early warning, and particularly relates to a customer overdue risk intelligent early warning method and system based on artificial intelligence. BACKGROUND
[0002] Overdue risk early warning is a mechanism for effectively predicting and intervening in overdue risk by performing multi-dimensional data analysis on user account status, consumption behavior, payment habits and related external factors to identify users who may have overdue behavior in advance and timely issue early warning prompts, thereby reducing service interruption risk, reducing operational losses and improving user experience.
[0003] In the prior art, the mechanism for overdue risk early warning usually only relies on setting a plurality of fixed account balance early warning thresholds, and when the account balance of a customer is lower than the corresponding early warning threshold, overdue risk early warning is performed. However, this static and single early warning method lacks in-depth analysis of the actual behavior and payment habits of the customer and cannot dynamically adjust according to the customer, and the customer often ignores the early warning message, resulting in service interruption due to forgetting to pay, thereby affecting the customer's use experience. SUMMARY
[0004] The purpose of the present application is to provide a customer overdue risk intelligent early warning method and system based on artificial intelligence, which can realize dynamic and personalized risk early warning, improve the fit of risk early warning and the actual payment needs of the customer, improve the use experience of the customer, and thereby effectively reduce the risk of service terminals.
[0005] To achieve the above purpose, the technical scheme is adopted as follows: According to the first aspect of the present application, a customer overdue risk intelligent early warning method based on artificial intelligence is provided, comprising the following steps: Obtaining the account balance of the customer, and if the account balance is lower than the preset initial early warning balance, performing initial risk early warning; Determining whether payment is completed after the initial risk early warning; if payment is not completed after the initial risk early warning, calculating state factor related values representing the payment state and the current period state; the state factors of the current period state include the current account balance, the current use rate, the current use duration and the current charging price; Comparing the plurality of state factor related values with the corresponding preset standard early warning values to obtain the related comparison results of the state factor related values; According to the related comparison results of the state factor related values, determining whether the related standards are met, and if the related standards are met, performing re-risk early warning.
[0006] The above technical solution provides an initial risk warning based on the customer's payment status. After the initial warning but before payment is completed, multiple status factors are periodically calculated and compared. If the relevant criteria are met, a second risk warning is issued. This dynamic risk warning system utilizes the correlation between the current periodic status and the representative payment status. By providing differentiated and personalized risk warnings based on the representative payment status of different customers, the system ensures that risk warnings align with customers' actual payment needs, reducing the likelihood of customers ignoring warning messages, effectively mitigating the risk of service interruption, and improving the customer experience.
[0007] According to one embodiment of the present invention, the step of calculating the state factor correlation value representing the payment status and the current cycle status includes: Determine the state factors of the current cycle state; The correlation value between the current period status and the corresponding status factor in the representative payment status is calculated using the following formula: ; In the formula, Representing the Each representative indicates their payment status. For the first Each value represents a state factor related to the payment status and the current cycle status; Representing the There are 1 state factors, totaling 1 One state factor; The current period state is the th The value of each state factor, For the first The first one representing the payment status The value of each state factor, For multiple The maximum difference between the values of the state factors.
[0008] Therefore, by analyzing customers' payment habits and actual behaviors using different status factors, the alignment between early warning plans and customer needs can be improved.
[0009] Status factors involve multiple aspects such as current account balance, current usage rate, current usage duration, and current billing price, comprehensively considering the impact of multiple factors on customers' payment habits, thereby improving the accuracy of personalized early warning solutions for different customers.
[0010] According to one embodiment of the present invention, determining the payment status includes the following steps: Obtain the customer's historical payment data, which includes the account balance at the time of payment, the usage rate at the time of payment, the usage duration at the time of payment, and the billing price at the time of payment; based on the preset balance period, the account balance is periodized when paying, and the payment times corresponding to each balance period are determined; based on the payment times corresponding to each balance period and the preset standard payment times, a representative payment state is determined; the state factors of the representative payment state include a representative account balance, a representative usage rate, a representative usage duration and a representative billing price.
[0011] The payment state corresponding to the balance period with the payment times higher than the preset standard payment times is the representative payment state.
[0012] According to the technical scheme, a plurality of representative payment states are determined according to the historical payment data of the customer, the payment habits of different customers are analyzed to generate personalized representative payment states, and the fitting degree of the obtained early warning scheme to the actual payment habits and needs of the customer is improved.
[0013] According to an embodiment of the present application, before the step of obtaining the historical payment data of the customer, the method further comprises: obtaining the data access permission of the customer; based on the data access permission, obtaining the historical payment data of the customer.
[0014] According to an embodiment of the present application, the representative account balance is the median value of the account balance of the corresponding balance period; the representative usage rate is the mean value of the plurality of usage rates of the corresponding balance period; the representative usage duration is the mean value of the plurality of usage durations of the corresponding balance period; the representative billing price is the mean value of the plurality of billing prices of the corresponding balance period.
[0015] According to an embodiment of the present application, according to the correlation comparison result of each state factor correlation value, if at least one state factor correlation value is greater than the corresponding preset standard early warning value, it is determined that the correlation meets the standard.
[0016] According to an embodiment of the present application, the step of performing the re-risk early warning comprises: determining the current account balance and the current usage rate of the customer; based on the current account balance and the current usage rate, calculating the predicted usage duration; based on the current account balance and the predicted usage duration, generating the re-early warning information.
[0017] According to the second aspect of the present application, an artificial intelligence-based customer overdue payment risk intelligent early warning device is provided, comprising: an initial early warning module, configured to obtain the account balance of the customer, and if the account balance is lower than the preset initial early warning balance, perform initial risk early warning; The tracking judgment module is configured to judge whether payment is completed after the initial risk warning; if payment is not completed after the initial risk warning, a state factor related value representing a payment state and a current period state is calculated; the state factor of the current period state includes a current account balance, a current use rate, a current use duration and a current charging price; The related value comparison module is configured to compare the plurality of state factor related values with corresponding preset standard warning values to obtain a related comparison result of each state factor related value. The re-warning module is configured to determine whether the relatedness meets the standard according to the related comparison result of each state factor related value, and perform a re-risk warning if the relatedness meets the standard.
[0018] According to a third aspect of the present application, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the AI-based customer overdue risk intelligent warning method of any of the above embodiments when executing the computer program.
[0019] According to a fourth aspect of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the AI-based customer overdue risk intelligent warning method of any of the above embodiments.
[0020] Compared with the prior art, the present application has at least the following beneficial effects: The AI-based customer overdue risk intelligent warning device, electronic device and computer readable storage medium provided by the present application also solve the problems raised in the background art.
[0021] 1. The present application performs initial risk warning according to the payment state of the customer; when the payment is not completed after the initial risk warning, a plurality of state factor related values are periodically calculated and compared, and when the relatedness meets the standard, a re-risk warning is performed. In this way, a dynamic risk warning scheme is formed by using the correlation between the current period state and the representative payment state; different customers are warned differently and individually according to their representative payment states, so that the risk warning is tailored to the actual payment needs of the customers, thereby reducing the possibility of the customers ignoring the warning messages, effectively reducing the risk of service interruption, and improving the customer experience.
[0022] 2. The present application analyzes the payment habits and actual behaviors of the customers by using different state factors, which can improve the fit of the warning scheme to the customer needs; the state factors involve the current account balance, the current use rate, the current use duration and the current charging price, and the influence of multiple factors on the payment habits of the customers is considered comprehensively, thereby improving the accuracy of the individualized warning scheme for different customers. Attached Figure Description
[0023] The accompanying drawings, which form part of this specification, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a flowchart of the intelligent early warning method for customer arrears risk based on artificial intelligence, as described in Embodiment 1 of the present invention. Figure 2 This is a flowchart illustrating the method for determining payment status in Embodiment 1 of the present invention; Figure 3 This is a structural block diagram of the intelligent early warning device for customer arrears risk based on artificial intelligence, which is embodiment 2 of the present invention. Figure 4 This is a schematic diagram of the structure of the electronic device in Embodiment 3 of the present invention.
[0024] Reference numerals in the attached figures: Electronic device 100; Memory 101; Processor 102; Computer program 103; Communication bus 104. Detailed Implementation
[0025] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.
[0026] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this invention is for describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.
[0027] Example 1 An AI-based intelligent early warning method for customer arrears risk, such as Figure 1 As shown, it includes the following steps: Obtain the customer's account balance; if the account balance is lower than the preset initial warning balance, issue an initial risk warning. Determine whether payment has been completed after the initial risk warning; if payment has not been completed after the initial risk warning, calculate the status factor correlation value representing the payment status and the current period status; the status factors of the current period status include the current account balance, current usage rate, current usage duration, and current billing price; Compare the relevant values of multiple state factors with the corresponding preset standard warning values to obtain the relevant comparison results of each state factor's relevant values; Based on the comparison results of the correlation values of each state factor, it is determined whether the correlation meets the standard. If the correlation meets the standard, a second risk warning is issued.
[0028] The above technical solution provides an initial risk warning based on the customer's payment status, rather than issuing warnings and payment reminders only after the customer's account is in arrears. After the initial risk warning and if payment is not completed, multiple status factors are periodically calculated and compared. If the relevant criteria are met, a second risk warning is issued. This dynamic risk warning system utilizes the correlation between the current periodic status and the representative payment status. By differentiating and personalizing risk warnings for different customers based on their representative payment status, the system ensures that risk warnings align with the customer's actual payment needs, reducing the likelihood of customers ignoring warning messages, effectively mitigating the risk of service interruption, and improving the customer experience.
[0029] For details, see Figure 1 The following is an AI-based intelligent early warning method for customer arrears risk.
[0030] S1. Obtain the customer's account balance. If the account balance is lower than the preset initial warning balance, issue an initial risk warning.
[0031] First, obtain data access permissions for the customer, and then obtain the customer's real-time account balance based on those permissions.
[0032] An initial risk warning is issued when a customer's account balance falls below the preset initial warning balance.
[0033] If the account balance falls below the initial warning balance, an initial warning is generated based on the current balance and the initial predicted usage duration. Then, using artificial intelligence technology, an initial warning notification is sent to the customer's mobile device, providing an initial risk warning.
[0034] S2. Determine whether payment has been completed after the initial risk warning; if payment has not been completed after the initial risk warning, calculate the correlation value of the status factor representing the payment status and the current period status.
[0035] After the initial risk warning is completed, the customer's real-time account balance is continuously monitored to determine whether the customer has completed the payment.
[0036] If payment is not completed after the initial risk warning, a periodic status correlation analysis is performed based on multiple representative payment statuses to calculate the correlation value between the representative payment status and the status factors of the current period. The status factors of the current period include the current account balance, current usage rate, current usage duration, and current billing price.
[0037] For the method of determining the payment status, please refer to [link / reference needed]. Figure 2 This includes the following steps: S(1) Obtains the customer's data access permissions.
[0038] S(2) Based on data access permissions, obtain the customer's historical payment data; historical payment data includes the account balance at the time of payment, the usage rate at the time of payment, the usage duration at the time of payment, and the billing price at the time of payment.
[0039] By identifying payments from historical payment data, the account balance at the time of each payment is determined, resulting in multiple payment balances. It is understandable that, except in some special circumstances, customers generally make payments before their payment account balance reaches zero. The payment balance is the remaining amount in the customer's payment account recorded in the historical payment data at the time of payment.
[0040] S(3) Based on the preset balance period, perform time period statistics on the account balance at the time of payment to determine the number of payments corresponding to each balance period.
[0041] The preset balance time period can be set according to the customer's payment habits, such as a balance of 0-10 yuan, 10-20 yuan, etc., and then the number of payments in different balance time periods is counted.
[0042] S(4) Determine the representative payment status based on the number of payments corresponding to each balance period and the preset standard number of payments; the payment status corresponding to the balance period with a number of payments higher than the preset standard number of payments is the representative payment status.
[0043] According to the order of the number of payments in the balance period statistics from most to least, the multiple balance periods are arranged, and according to the preset standard number of payments, the first few balance periods are selected as representative periods, and the representative payment status corresponding to the multiple representative periods is determined.
[0044] The preset standard number of payments can be set according to the customer's historical payment habits, such as 2 payments or 5 payments.
[0045] Status factors representing payment status include account balance, usage rate, usage duration, and billing price.
[0046] In addition, the steps for calculating the correlation values of state factors representing payment status and the current cycle status include: Determine the status factors for the current period. In this embodiment, the relevant comparison period can be set to 24 hours; the status factors for the current period include the current account balance, current usage rate, current usage duration, and current billing price. Obtain current status data such as the current account balance, current usage rate, current usage duration, and current billing price for the current period; according to multiple status factors, obtain representative status data such as representative account balance, representative usage rate, representative usage duration, and representative billing price corresponding to multiple representative payment statuses.
[0047] In this embodiment, the account balance represents the median of the account balance during the corresponding balance period; the usage rate represents the average of multiple usage rates during the corresponding balance period; the usage duration represents the average of multiple usage durations during the corresponding balance period; and the billing price represents the average of multiple billing prices during the corresponding balance period.
[0048] The correlation value between the current period status and the corresponding status factor in the representative payment status is calculated using the following formula: ; In the formula, Representing the Each representative indicates their payment status. For the first Each value represents a state factor related to the payment status and the current cycle status; Representing the There are 1 state factors, totaling 1 There are 4 state factors, and in this embodiment, n=4. The current period state is the th The value of each state factor, For the first The first one representing the payment status The value of each state factor, For multiple The maximum difference between the values of the state factors.
[0049] Therefore, by analyzing customers' payment habits and actual behaviors using different status factors, the alignment between early warning plans and customer needs can be improved.
[0050] S3. Compare the relevant values of multiple state factors with the corresponding preset standard warning values to obtain the relevant comparison results of each state factor's relevant values.
[0051] The preset standard warning value can be set by the user or according to the customer's payment habits.
[0052] S4. Based on the correlation comparison results of the correlation values of each state factor, determine whether the correlation meets the standard. If the correlation meets the standard, issue another risk warning.
[0053] The relevant values of multiple state factors are compared with the preset standard warning value to obtain the relevant comparison results. It is then determined whether the relevant standards are met. Based on the relevant comparison results, if at least one state relevant value is greater than the standard warning value, the relevant standards are determined to be met.
[0054] At this point, based on the current account balance and current usage rate, the predicted usage duration is calculated again, and a second warning message is generated based on the current account balance and the predicted usage duration. Then, based on artificial intelligence technology, a second warning message is sent to the customer's mobile device, thereby achieving a second risk warning for the customer.
[0055] Thus, when the relevant values of various status factors meet the standards, a second risk warning is issued. The content of this second risk warning is based on the current account status of the customer. Artificial intelligence technology is used to calculate and predict usage duration based on the current account balance and current usage rate. In this way, based on the analysis of the customer's payment habits, the future usage duration that the customer's account balance can meet is predicted based on the current account balance and the customer's usage rate. Based on this, dynamic and personalized second risk warning information is generated, enhancing the alignment with customer habits.
[0056] Furthermore, when calculating the predicted usage time, back propagation (BP) neural networks, recurrent neural networks (RNNs), long short-term memory (LSTM) neural networks, and convolutional neural networks (CNNs)-LSTM neural networks can be used to improve the accuracy of the predicted usage time. If necessary, the impact of weather, season, weekdays, and holidays on usage rates can also be considered to further enhance the accuracy of the predicted usage time.
[0057] The AI-based intelligent early warning method for customer arrears risk adopted in this embodiment provides an initial risk warning based on the customer's payment status. After the initial risk warning, if payment is not completed, multiple status factors are periodically calculated and compared. If the relevant criteria are met, a second risk warning is issued. In this way, a dynamic risk warning scheme is formed by utilizing the correlation between the current periodic status and the representative payment status. By providing differentiated and personalized risk warnings to different customers based on their representative payment status, the risk warnings are tailored to the customer's actual payment needs, thereby reducing the possibility of customers ignoring warning messages, effectively reducing the risk of service interruption, and improving the customer experience.
[0058] This embodiment of the AI-based intelligent early warning method for customer arrears risk performs habit matching on status data such as account balance, usage rate, usage duration, and billing price based on the user's payment history data. It is a process of analysis and early warning based on the user's payment habits in a non-arrears state, and can improve the timing of risk warnings and the relevance between risk warning content and customer habits, reduce the possibility of customers ignoring warning messages, and improve the customer's user experience.
[0059] Example 2 like Figure 3 As shown, based on the same inventive concept as the above embodiments, the present invention also provides an intelligent early warning device for customer arrears risk based on artificial intelligence, comprising: The initial warning module is used to obtain the customer's account balance. If the account balance is lower than the preset initial warning balance, an initial risk warning will be issued. The tracking and judgment module is used to determine whether payment has been completed after the initial risk warning. If payment has not been completed after the initial risk warning, the module calculates the correlation values of status factors representing the payment status and the current period status. The status factors of the current period status include the current account balance, current usage rate, current usage duration, and current billing price. The correlation value comparison module is used to compare the correlation values of multiple state factors with the corresponding preset standard warning values to obtain the correlation comparison results of each state factor correlation value. The re-early warning module is used to determine whether the relevant standards are met based on the comparison results of the relevant values of each state factor. If the relevant standards are met, a re-risk warning is issued.
[0060] Example 3 like Figure 4 As shown, the present invention also provides an electronic device 100 for realizing intelligent early warning of customer arrears risk based on artificial intelligence.
[0061] The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104.
[0062] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the intelligent early warning method for customer arrears risk based on artificial intelligence in Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.
[0063] The memory 101 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.
[0064] At least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 102 may be a microprocessor or any conventional processor. Processor 102 is the control center of electronic device 100, connecting various parts of electronic device 100 via various interfaces and lines.
[0065] The memory 101 in the electronic device 100 stores multiple instructions to implement an AI-based intelligent early warning method for customer arrears risk, and the processor 102 can execute multiple instructions to achieve the following: Obtain the customer's account balance; if the account balance is lower than the preset initial warning balance, issue an initial risk warning. Determine whether payment has been completed after the initial risk warning; if payment has not been completed after the initial risk warning, calculate the correlation value of the status factor representing the payment status and the current period status. Compare the relevant values of multiple state factors with the corresponding preset standard warning values to obtain the relevant comparison results of each state factor's relevant values; Based on the comparison results of the correlation values of each state factor, it is determined whether the correlation meets the standard. If the correlation meets the standard, a second risk warning is issued.
[0066] Example 4 If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).
[0067] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0068] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0069] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0070] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0071] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.
Claims
1. An artificial intelligence-based customer arrears risk intelligent early warning method, characterized in that, The method comprises the following steps: obtaining the account balance of the customer, and if the account balance is lower than the preset initial warning balance, performing initial risk warning; determining whether payment is completed after the initial risk warning; if payment is not completed after the initial risk warning, calculating a state factor related value representing the payment state and the current period state; the state factor of the current period state includes the current account balance, the current use rate, the current use time length and the current charging price; comparing the plurality of state factor related values with the corresponding preset standard warning values to obtain the related comparison results of the state factor related values; determining whether the related standards are met according to the related comparison results of the state factor related values, and if the related standards are met, performing secondary risk warning.
2. The intelligent warning method according to claim 1, wherein the step of calculating the state factor related value representing the payment state and the current period state comprises: determining the state factor of the current period state; calculating the state factor related value of the current period state and the corresponding state factor in the payment state according to the following formula:
3. The intelligent warning method according to claim 1, wherein the determination of the payment state comprises the following steps: ； In the formula, represents the first representative payment state, is the value of the first representative payment state and the state factor of the current period state; represents the first state factor, and there are state factors in total; is the value of the first state factor of the current period state, is the value of the first state factor of the first representative payment state, is the maximum difference value of the values of the plurality of first state factors. obtaining the historical payment data of the customer, wherein the historical payment data includes the account balance at the time of payment; performing period statistics on the account balance at the time of payment based on the preset balance period to determine the payment times corresponding to each balance period; determining the representative payment state based on the payment times corresponding to each balance period and the preset standard payment times; the state factor of the representative payment state includes the representative account balance, the representative use rate, the representative use time length and the representative charging price.
4. The intelligent warning method according to claim 3, wherein before the step of obtaining the historical payment data of the customer, the method further comprises: obtaining the data access permission of the customer; obtaining the historical payment data of the customer based on the data access permission.
5. The intelligent warning method according to claim 3, wherein the representative account balance is the median value of the account balance corresponding to the balance period; the representative use rate is the average value of the plurality of use rates corresponding to the balance period; the representative use time length is the average value of the plurality of use time lengths corresponding to the balance period; the representative charging price is the average value of the plurality of charging prices corresponding to the balance period.
6. The intelligent warning method according to claim 1, wherein in the step of determining whether the related standards are met according to the related comparison results of the state factor related values, if at least one state factor related value is greater than the corresponding preset standard warning value, it is determined that the related standards are met.
7. The intelligent warning method according to claim 1, wherein the step of performing secondary risk warning if the related standards are met comprises: determining the current account balance and the current use rate of the customer; calculating the predicted use time length based on the current account balance and the current use rate; generating the secondary warning information based on the current account balance and the predicted use time length. The method comprises the following steps: an initial warning module is configured to obtain the account balance of the customer, and if the account balance is lower than the preset initial warning balance, perform initial risk warning; 8. The customer arrear risk intelligent early warning device based on artificial intelligence, characterized in that, The tracking judgment module is configured to judge whether payment is completed after the initial risk warning; if payment is not completed after the initial risk warning, a state factor related value representing a payment state and a current period state is calculated; the state factor of the current period state includes a current account balance, a current use rate, a current use time length, and a current charging price; The related value comparison module is configured to compare the plurality of state factor related values with corresponding preset standard warning values, and obtain a related comparison result of each state factor related value; The second warning module is configured to determine whether the related values meet the standards according to the related comparison result of each state factor related value, and perform a second risk warning if the related values meet the standards.
9. An electronic device, comprising: The computer readable storage medium stores at least one instruction, and the at least one instruction is executed by the processor to implement the artificial intelligence-based customer overdue risk intelligent warning method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores at least one instruction, and the at least one instruction is executed by the processor to implement the artificial intelligence-based customer overdue risk intelligent warning method according to any one of claims 1-7.