Arrears early warning method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide an arrears early warning method and device, electronic equipment and storage medium, the method comprises: obtaining the current remaining amount of a user, the monthly package amount, the historical average arrears amount and the remaining days until the next payment, inputting the monthly subscription amount, the historical average arrears amount and the remaining days until the next payment into an arrears early warning threshold prediction model to obtain an arrears early warning threshold, wherein the arrears early warning threshold prediction model is obtained by training the historical arrears related data of the user, and the current remaining amount and the arrears early warning threshold are used to trigger the early warning behavior for the user. In the embodiments of the present application, the current remaining amount of the user, the monthly package amount, the historical average arrears amount and the remaining days until the next payment are combined to predict the arrears early warning threshold of each user, the accuracy of the arrears early warning threshold is improved, and the predicted arrears early warning threshold is adapted to the user.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a method for early warning of overdue payments, a device for early warning of overdue payments, an electronic device, and a computer-readable storage medium. Background Technology

[0002] In current government and enterprise business, user arrears leading to business system interruptions may cause significant losses to users, which is not conducive to maintaining user relationships and recovering arrears. If the user manager then has to follow up on the payment after the arrears are due, this method is not timely and can easily lead to an excessive accumulation of arrears.

[0003] Traditional early warning methods involve setting a threshold; when this threshold is exceeded, an alert is triggered. In the context of user overdue payment alerts, this means setting a fixed threshold for a user's subscription. When the user's remaining balance falls below this threshold, the account manager is notified to renew the subscription. However, because each user's spending habits differ, setting a fixed threshold is inaccurate and cannot effectively adapt to each user. For example, a user with low spending habits might not incur any overdue payments even if their remaining balance falls below the fixed threshold. In such cases, issuing an alert when the remaining balance is below the threshold would be ineffective, leading to a poor user experience. Summary of the Invention

[0004] This invention provides a method, device, electronic device, and storage medium for overdue payment early warning, in order to solve the problem that setting a fixed early warning threshold is not accurate enough and cannot effectively adapt to each user because each user's consumption situation is different.

[0005] This invention discloses a method for early warning of overdue payments, the method comprising:

[0006] Get the user's current remaining balance, monthly plan amount, historical average outstanding amount, and number of days remaining until the next payment;

[0007] The monthly subscription amount, the historical average outstanding amount, and the number of days remaining until the next payment are input into the overdue payment warning threshold prediction model to obtain the overdue payment warning threshold; wherein, the overdue payment warning threshold prediction model is trained using the user's historical overdue payment data;

[0008] The system triggers an alert for the user based on the current remaining balance and the overdue payment warning threshold.

[0009] Optionally, obtain the user's historical average outstanding amount, including:

[0010] Obtain the user's total historical outstanding amount and the number of historical outstanding payment periods;

[0011] The ratio of the total historical arrears to the number of historical arrears periods is taken as the user's historical average arrears.

[0012] Optionally, after inputting the monthly product order payment amount, the historical average outstanding amount, and the number of days remaining until the next payment into the outstanding payment warning threshold prediction model to obtain the outstanding payment warning threshold, the method further includes:

[0013] The overdue payment warning threshold is verified for compliance to determine whether the overdue payment warning threshold is abnormal;

[0014] When it is determined that the overdue payment warning threshold is abnormal, the abnormal overdue payment warning threshold is recorded in the log.

[0015] When it is determined that the overdue payment warning threshold is normal, the step of triggering a warning action for the user based on the current remaining amount and the overdue payment warning threshold is executed.

[0016] Optionally, triggering a warning action for the user based on the current remaining amount and the overdue payment warning threshold includes:

[0017] Determine whether the current remaining amount is lower than the overdue payment warning threshold;

[0018] If the current remaining amount is lower than or equal to the overdue payment warning threshold, a warning action is triggered for the user.

[0019] Optionally, the alert behaviors for users include at least SMS alert behaviors and voice alert behaviors.

[0020] Optionally, before inputting the monthly subscription amount, the historical average outstanding amount, and the number of days remaining until the next payment into the overdue payment warning threshold prediction model, the method further includes:

[0021] Obtain the user's historical overdue payment data, which includes historical monthly package amount, historical overdue amount, historical overdue payment period, and historical payment time.

[0022] The overdue payment warning threshold prediction model is trained based on the historical overdue payment data to obtain the trained overdue payment warning threshold prediction model.

[0023] Optionally, after triggering the warning action for the user based on the current remaining amount and the overdue payment warning threshold, the method further includes:

[0024] Get the user's outstanding balance for the current month;

[0025] The overdue payment warning threshold prediction model is trained using the current month's overdue amount, the historical average overdue amount, the current month's package amount, and the number of days remaining until the next payment, to obtain an optimized overdue payment warning threshold prediction model.

[0026] This invention also discloses an overdue payment early warning device, characterized in that it includes:

[0027] The data acquisition module is used to obtain the user's current remaining balance, monthly package amount, historical average outstanding amount, and number of days remaining until the next payment.

[0028] The early warning threshold prediction module is used to input the monthly subscription amount, the historical average arrears amount, and the number of days remaining until the next payment into the arrears early warning threshold prediction model to obtain the arrears early warning threshold; wherein, the arrears early warning threshold prediction model is trained by the user's historical arrears data;

[0029] The warning behavior triggering module is used to trigger warning behaviors for users based on the current remaining amount and the overdue payment warning threshold.

[0030] Optionally, the data acquisition module includes:

[0031] The data acquisition submodule is used to obtain the user's total historical arrears amount and the number of historical arrears periods;

[0032] The average outstanding amount calculation submodule is used to take the ratio of the total historical outstanding amount to the number of historical outstanding periods as the user's historical average outstanding amount.

[0033] Optionally, it also includes:

[0034] The threshold verification module is used to verify the compliance of the overdue payment warning threshold and determine whether the overdue payment warning threshold is abnormal.

[0035] The threshold recording module is used to record the abnormal overdue payment warning threshold in the log when it is determined that the overdue payment warning threshold is abnormal.

[0036] The early warning execution module is used to execute the early warning behavior triggering module when it is determined that the overdue payment early warning threshold is normal.

[0037] Optionally, the warning behavior triggering module includes:

[0038] The threshold determination submodule is used to determine whether the current remaining amount is lower than the overdue payment warning threshold;

[0039] The warning behavior triggering submodule is used to trigger a warning behavior for the user if the current remaining amount is lower than or equal to the overdue payment warning threshold.

[0040] Optionally, the alert behaviors for users include at least SMS alert behaviors and voice alert behaviors.

[0041] Optionally, it also includes:

[0042] The data acquisition module is also used to acquire the user's historical arrears data, which includes historical monthly package amount, historical arrears amount, historical arrears period number and historical payment time.

[0043] The model training module is used to train the overdue payment warning threshold prediction model to be trained based on the historical overdue payment related data, so as to obtain the trained overdue payment warning threshold prediction model.

[0044] Optionally, it also includes:

[0045] The data acquisition module is also used to obtain the user's outstanding monthly fee amount;

[0046] The model training module is also used to train the overdue payment warning threshold prediction model using the current month's overdue amount, the historical average overdue amount, the current month's package amount, and the number of days remaining until the next payment, so as to obtain the optimized overdue payment warning threshold prediction model.

[0047] This invention also discloses an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0048] The memory is used to store computer programs;

[0049] When the processor executes a program stored in the memory, it implements the method described in the embodiments of the present invention.

[0050] This invention also discloses a computer-readable storage medium storing instructions that, when executed by one or more processors, cause the processors to perform the methods described in this invention.

[0051] The embodiments of the present invention have the following advantages: The current remaining balance, monthly package amount, historical average outstanding amount, and number of days remaining until the next payment are obtained from the user. These data are then input into an overdue payment warning threshold prediction model to obtain the overdue payment warning threshold. This model can combine multiple dimensions of data, such as the user's current remaining balance, monthly package amount, historical average outstanding amount, and number of days remaining until the next payment, to predict the overdue payment warning threshold for each user, thereby improving the accuracy of the overdue payment warning threshold and ensuring that the predicted overdue payment warning threshold is suitable for the user, avoiding invalid warnings due to inaccurate overdue payment warning thresholds. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating the steps of an overdue payment early warning method provided in an embodiment of the present invention;

[0053] Figure 2 This is a schematic diagram of an overdue payment early warning process provided in an embodiment of the present invention;

[0054] Figure 3 This is a structural block diagram of an overdue payment early warning device provided in an embodiment of the present invention;

[0055] Figure 4 This is a block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0056] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0057] Reference Figure 1 The diagram illustrates a flowchart of a pre-payment overdue payment warning method provided in an embodiment of the present invention, which may specifically include the following steps:

[0058] Step 101: Obtain the user's current remaining balance, monthly package amount, historical average outstanding amount, and number of days remaining until the next payment.

[0059] Among them, the current remaining amount is the amount remaining in the user's account; the monthly package amount is the amount corresponding to the various packages and products ordered by the user, which is also the amount payable for the current month; the historical average arrears amount is the average of the arrears amount for each time in history; and the number of days remaining until the next payment is the number of days from the current time to the next payment time.

[0060] Specifically, based on actual business traffic conditions, scheduled tasks can be set up during off-peak hours to retrieve consumption data such as the current remaining balance in a user's account, the monthly plan amount, the historical average outstanding balance, and the number of days remaining until the next payment. In practical applications, user consumption data can be retrieved in batches.

[0061] Step 102: Input the monthly subscription amount, the historical average arrears amount, and the number of days remaining until the next payment into the arrears warning threshold prediction model to obtain the arrears warning threshold.

[0062] The overdue payment warning threshold prediction model is trained using users' historical overdue payment data.

[0063] Specifically, after obtaining the user's current remaining balance, monthly package amount, historical average arrears amount, and number of days remaining until the next payment, the current remaining balance, monthly package amount, historical average arrears amount, and number of days remaining until the next payment are input into the arrears warning threshold prediction model. The arrears warning threshold for the user is then predicted through the arrears warning threshold prediction model.

[0064] Step 103: Trigger a warning action for the user based on the current remaining amount and the overdue payment warning threshold.

[0065] Specifically, by using the overdue payment warning threshold prediction model, warning actions can be triggered for users based on the current remaining balance and the overdue payment warning threshold. For example, the current remaining balance is compared with the overdue payment warning threshold, and a warning action is triggered for the user when the current remaining balance is lower than the overdue payment warning threshold.

[0066] In this embodiment of the invention, the user's current remaining balance, monthly package amount, historical average arrears amount, and number of days remaining until the next payment are obtained. These data are then input into the arrears warning threshold prediction model to obtain the arrears warning threshold. This model can combine multiple dimensions of data, such as the user's current remaining balance, monthly package amount, historical average arrears amount, and number of days remaining until the next payment, to predict the arrears warning threshold for each user. This improves the accuracy of the arrears warning threshold, ensuring that the predicted arrears warning threshold is suitable for the user and avoiding invalid warnings due to inaccurate thresholds.

[0067] Based on the above embodiments, modified embodiments of the above embodiments are proposed. It should be noted that, in order to keep the description brief, only the differences from the above embodiments are described in the modified embodiments.

[0068] In an optional embodiment of the present invention, obtaining the user's historical average arrears amount includes: obtaining the user's total historical arrears amount and the number of historical arrears periods; and using the ratio of the total historical arrears amount to the number of historical arrears periods as the user's historical average arrears amount.

[0069] Specifically, by obtaining the user's historical outstanding amount and the number of historical outstanding periods D, and calculating the total historical outstanding amount d using each historical outstanding amount, the ratio of the total historical outstanding amount d to the number of historical outstanding periods D is calculated to obtain the historical average outstanding amount X2, as follows:

[0070]

[0071] In an optional embodiment of the present invention, after inputting the monthly subscription amount, the historical average outstanding amount, and the number of days remaining until the next payment into the overdue payment warning threshold prediction model to obtain the overdue payment warning threshold, the method further includes: performing a compliance check on the overdue payment warning threshold to determine whether the overdue payment warning threshold is abnormal; when the overdue payment warning threshold is determined to be abnormal, recording the abnormal overdue payment warning threshold in the log; when the overdue payment warning threshold is determined to be normal, executing a step to trigger a warning behavior for the user based on the current remaining amount and the overdue payment warning threshold.

[0072] Specifically, there are various ways to verify the compliance of the overdue payment warning threshold. For example, you can check some key data information that users will use in subsequent business, such as industry and certificate information, to determine whether there is any missing or incomplete key data information. If it is determined that there is any missing or incomplete key data information, then the overdue payment warning threshold is determined to be abnormal. Alternatively, you can determine whether the overdue payment warning threshold is within a reasonable range. If the overdue payment warning threshold is not within a reasonable range, then the overdue payment warning threshold is determined to be abnormal.

[0073] After determining that the overdue payment warning threshold is abnormal, the abnormal threshold is logged, and corresponding processing is then performed. When the overdue payment warning threshold is determined to be normal, it can be used to issue a warning to the user, specifically triggering the warning action based on the current remaining balance and the overdue payment warning threshold.

[0074] In an optional embodiment of the present invention, triggering a warning action for the user based on the current remaining amount and the overdue payment warning threshold includes: determining whether the current remaining amount is lower than the overdue payment warning threshold; if the current remaining amount is lower than or equal to the overdue payment warning threshold, triggering a warning action for the user.

[0075] The warning behaviors for users include at least SMS warning behaviors, voice warning behaviors, and application prompts, which can be set according to actual needs. This embodiment of the invention does not impose any restrictions on this.

[0076] Specifically, after predicting the overdue payment warning threshold, the current remaining amount in the user's account can be compared with the overdue payment warning threshold. When the current remaining amount is lower than or equal to the overdue payment warning threshold, a warning action is triggered for the user.

[0077] In an optional embodiment of the present invention, before inputting the monthly subscription amount, the historical average arrears amount, and the number of days remaining until the next payment into the arrears warning threshold prediction model, the method further includes: obtaining the user's historical arrears-related data, which includes historical monthly subscription amount, historical arrears amount, historical arrears period, and historical payment time; and training the arrears warning threshold prediction model to be trained based on the historical arrears-related data to obtain the trained arrears warning threshold prediction model.

[0078] Among them, historical payment time refers to the historical deduction time. Specifically, the user's past arrears and renewal history data is obtained, including historical monthly package amount, historical arrears amount, historical number of arrears period, and historical payment time. Then, the arrears warning threshold prediction model to be trained is trained using historical monthly package amount, historical arrears amount, historical number of arrears period, and historical payment time. The specific training process is as follows:

[0079] Randomly select a historical time point, obtain the monthly package amount (X1) for that month from the historical monthly package amount, determine the historical arrears amount and the number of historical arrears in the months prior to that time point, calculate the historical average arrears amount (X2) before that time point based on the historical arrears amount and the number of historical arrears in the period, and calculate the remaining number of days (X3) from that time point to the current month's payment deadline. Input X1, X2, and X3 into the multiple linear regression base model (the arrears warning threshold prediction model to be trained), as follows:

[0080] y = b0 + b1x1 + b2x2 + b3x3 + ε

[0081] In the formula: ε is the estimation error between the predicted arrears threshold and the actual arrears data; y is the predicted user warning threshold (arrears warning threshold); x1 is the monthly production and sales fee payable (monthly package amount); x2 is the historical average arrears amount; x3 is the number of days remaining until the next payment; b0, b1, b2, and b3 are regression parameters to be calculated. b0 is a constant term; b1's practical significance is that the higher the monthly fee payable, the greater the likelihood of the user incurring arrears; b2 represents the user's historical credit record, which shows that the more times a user has incurred arrears in the past, the greater the likelihood of incurring arrears this time, thus requiring an increase in the arrears warning threshold; b3 represents the impact of getting closer to the payment date on the likelihood of arrears.

[0082] In the first training, ε is set to 0. Then, ε is calculated based on the predicted y and the actual amount of arrears in the current month (historical amount of arrears), and b0, b1, b2 and b3 are adjusted accordingly. In the subsequent training, ε is calculated using the predicted y and the actual amount of arrears in the current month.

[0083] After training the above model with a certain number of historical samples, if the difference between the predicted y and the current historical arrears amount is less than a preset threshold, or if the difference between the predicted y and the current historical arrears amount converges, the training of the arrears warning threshold prediction model to be trained is completed.

[0084] In an optional embodiment of the present invention, after triggering the warning behavior for the user based on the current remaining amount and the overdue payment warning threshold, the method further includes: obtaining the user's overdue amount for the current month; and training the overdue payment warning threshold prediction model using the overdue amount for the current month, the historical average overdue amount, the current month's package amount, and the number of days remaining until the next payment, to obtain an optimized overdue payment warning threshold prediction model.

[0085] Specifically, after triggering a warning action for the user based on the current remaining amount and the overdue payment warning threshold, if the user still fails to pay and is still in arrears after the monthly payment date, then the overdue amount for the current month is obtained. The historical average overdue amount, the current month's package amount, and the remaining days until the next payment are input into the overdue payment warning threshold prediction model, and the overdue payment warning threshold for the current month is output. Based on the difference between the overdue payment warning threshold and the current month's overdue amount, b0, b1, b2, b3, and / or ε in the warning threshold prediction model are adjusted to update and optimize the overdue payment warning threshold prediction model, so as to maintain the accuracy of the overdue payment warning threshold prediction model.

[0086] To better understand the embodiments of the present invention, please refer to... Figure 2 An example is provided.

[0087] Step 1: Establish a data model for user arrears and renewals (arrears warning threshold prediction model / arrears warning model)

[0088] By collecting users' past arrears and renewal history data, including user product order data, user renewal history data, user remaining balance data, user historical credit data, and other arrears-related content, and after cleaning the noisy data, a user arrears and renewal data model is established based on the multiple linear regression algorithm.

[0089] Establish a basic model for multiple linear regression.

[0090] y = b0 + b1x1 + b2x2 + b3x3 + ε

[0091] Where ε represents the estimation error between the predicted arrears threshold and the actual arrears data, y represents the predicted user warning threshold, x1 represents the monthly production and sales fees payable, x2 represents the average historical arrears amount, and x3 represents the number of days remaining until the next payment; b0, b1, b2, and b3 are regression parameters to be calculated. The practical significance of b1 is that the higher the monthly fees payable, the greater the likelihood of arrears for the user; b2 represents the user's historical credit record, showing that the more times a user has arrears in the past, the greater the likelihood of arrears this time, thus requiring a higher arrears warning threshold; b3 represents the impact of approaching the payment date on the likelihood of arrears.

[0092] Let D be the number of billing periods with a history of arrears, and d be the historical arrears amount. Assuming the historical billing periods are not empty, the value of x2 is obtained according to the formula.

[0093]

[0094] Therefore, based on the user's overdue payment and renewal data model, the appropriate warning threshold for each user can be calculated.

[0095] Step 2: Batch processing of user data

[0096] Based on the actual system deployment, a scheduled task is set during the off-peak hours of the business system to import the existing user and product information into the model in batches for data processing. By referring to the user's historical arrears data and product data, the arrears warning threshold for each user is updated.

[0097] Step 3: Update the user arrears threshold

[0098] Perform compliance verification on the synchronized data, retain and process user data with abnormal data separately, and synchronize and update the remaining normal user data to the arrears threshold data table.

[0099] Step 4: Trigger an alert based on the processing result.

[0100] After the results are synchronized, the task scheduling system triggers the early warning interfaces written in different business systems. These interfaces are compared with the overdue payment threshold for each user, and tasks are assigned to the user managers corresponding to users who meet the early warning conditions, or different early warning methods are executed according to business logic.

[0101] Step 5: Update the user's alert model after the alert action is completed.

[0102] After receiving feedback on the warning behavior in step 4, i.e. after reminding the user of the overdue payment, the user behavior is input into the warning model, the relevant historical data of the user is updated, and the model is trained so that the warning threshold of the user can be dynamically adjusted when the next task is executed.

[0103] In the above embodiments, a unique threshold indicator is set for each user. This threshold is derived by analyzing the user's outstanding payment information, product information, and renewal data through an established business data early warning model. Unlike the traditional method that uses a single threshold to determine the early warning behavior for all data, this method first calculates the remaining time that the current account balance can support by combining all services under the user's subscription status. Users with insufficient remaining time and outstanding payments are directly marked as users requiring early warning. For the remaining users, the user's willingness to renew is determined by their historical renewal data, and the user's credit index is calculated by combining the user's outstanding payment history data. Based on these indicators, an early warning threshold is dynamically set for each user, thereby achieving early warning for users with low credit indices and low renewal willingness, ensuring that the renewal operation is completed before the subscribed services are interrupted, avoiding the impact of outstanding payments on the user's business, and also reducing the amount of outstanding payments for government and enterprise services to a certain extent.

[0104] Single-threshold early warning mechanisms cannot meet the needs of changing business environments and lack timely and accurate warning effects, regardless of data format or development language. By adopting the embodiments of this invention, different early warning conditions can be dynamically calculated based on different users, different services, and different renewal history data. This technology can improve the reliability of early warning data, ensure the stable and secure operation of user services, reduce the occurrence of user arrears, and to a certain extent reduce the total amount of arrears.

[0105] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0106] Reference Figure 3 The diagram shows a structural block diagram of an overdue payment early warning device provided in an embodiment of the present invention, which may specifically include the following modules:

[0107] Data acquisition module 301 is used to acquire the user's current remaining balance, monthly package amount, historical average arrears amount, and number of days remaining until the next payment.

[0108] The early warning threshold prediction module 302 is used to input the monthly subscription amount, the historical average arrears amount, and the number of days remaining until the next payment into the arrears early warning threshold prediction model to obtain the arrears early warning threshold; wherein, the arrears early warning threshold prediction model is trained by the user's historical arrears related data;

[0109] The warning behavior triggering module 303 is used to trigger a warning behavior for the user based on the current remaining amount and the overdue payment warning threshold.

[0110] Optionally, the data acquisition module includes:

[0111] The data acquisition submodule is used to obtain the user's total historical arrears amount and the number of historical arrears periods;

[0112] The average outstanding amount calculation submodule is used to take the ratio of the total historical outstanding amount to the number of historical outstanding periods as the user's historical average outstanding amount.

[0113] Optionally, it also includes:

[0114] The threshold verification module is used to verify the compliance of the overdue payment warning threshold and determine whether the overdue payment warning threshold is abnormal.

[0115] The threshold recording module is used to record the abnormal overdue payment warning threshold in the log when it is determined that the overdue payment warning threshold is abnormal.

[0116] The early warning execution module is used to execute the early warning behavior triggering module when it is determined that the overdue payment early warning threshold is normal.

[0117] Optionally, the warning behavior triggering module includes:

[0118] The threshold determination submodule is used to determine whether the current remaining amount is lower than the overdue payment warning threshold;

[0119] The warning behavior triggering submodule is used to trigger a warning behavior for the user if the current remaining amount is lower than or equal to the overdue payment warning threshold.

[0120] Optionally, the alert behaviors for users include at least SMS alert behaviors and voice alert behaviors.

[0121] Optionally, it also includes:

[0122] The data acquisition module is also used to acquire the user's historical arrears data, which includes historical monthly package amount, historical arrears amount, historical arrears period number and historical payment time.

[0123] The model training module is used to train the overdue payment warning threshold prediction model to be trained based on the historical overdue payment related data, so as to obtain the trained overdue payment warning threshold prediction model.

[0124] Optionally, it also includes:

[0125] The data acquisition module is also used to obtain the user's outstanding monthly fee amount;

[0126] The model training module is also used to train the overdue payment warning threshold prediction model using the current month's overdue amount, the historical average overdue amount, the current month's package amount, and the number of days remaining until the next payment, so as to obtain the optimized overdue payment warning threshold prediction model.

[0127] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0128] In addition, this invention also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described data acquisition method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0129] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described data acquisition method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0130] Figure 4 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0131] The electronic device 400 includes, but is not limited to, components such as: a radio frequency unit 401, a network module 402, an audio output unit 403, an input unit 404, a sensor 405, a display unit 406, a user input unit 407, an interface unit 408, a memory 409, a processor 410, and a power supply 411. Those skilled in the art will understand that... Figure 4 The electronic device structures shown are not intended to limit the electronic device. An electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements. In embodiments of the present invention, the electronic device includes, but is not limited to, mobile phones, tablet computers, laptops, PDAs, in-vehicle terminals, wearable devices, and pedometers.

[0132] It should be understood that, in this embodiment of the invention, the radio frequency unit 401 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink data from the base station and processes it with the processor 410; additionally, it transmits uplink data to the base station. Typically, the radio frequency unit 401 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc. Furthermore, the radio frequency unit 401 can also communicate with networks and other devices through a wireless communication system.

[0133] The electronic device provides users with wireless broadband internet access through network module 402, such as helping users send and receive emails, browse web pages, and access streaming media.

[0134] The audio output unit 403 can convert audio data received by the radio frequency unit 401 or the network module 402 or stored in the memory 409 into audio signals and output them as sound. Furthermore, the audio output unit 403 can also provide audio output related to specific functions performed by the electronic device 400 (e.g., call signal reception sound, message reception sound, etc.). The audio output unit 403 includes a speaker, a buzzer, and a receiver, etc.

[0135] Input unit 404 is used to receive audio or video signals. Input unit 404 may include a graphics processing unit (GPU) 4041 and a microphone 4042. The GPU 4041 processes image data of still images or videos acquired by an image capture device (such as a camera) in video capture mode or image capture mode. The processed image frames can be displayed on display unit 406. The image frames processed by GPU 4041 can be stored in memory 409 (or other storage medium) or transmitted via radio frequency unit 401 or network module 402. Microphone 4042 can receive sound and process such sound into audio data. The processed audio data can be converted into a format that can be transmitted to a mobile communication base station via radio frequency unit 401 in telephone call mode.

[0136] The electronic device 400 also includes at least one sensor 405, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 4061 according to the ambient light level, and the proximity sensor can turn off the display panel 4061 and / or backlight when the electronic device 400 is moved to the ear. As a type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used to identify the posture of the electronic device (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc. The sensor 405 may also include a fingerprint sensor, pressure sensor, iris sensor, molecular sensor, gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc., which will not be described in detail here.

[0137] The display unit 406 is used to display information input by the user or information provided to the user. The display unit 406 may include a display panel 4061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0138] User input unit 407 can be used to receive input numerical or character information, and generate key signal inputs related to user settings and function control of electronic devices. Specifically, user input unit 407 includes a touch panel 4071 and other input devices 4072. Touch panel 4071, also known as a touch screen, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near touch panel 4071). Touch panel 4071 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 410, which receives and executes commands from the processor 410. In addition, touch panel 4071 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. Besides touch panel 4071, user input unit 407 may also include other input devices 4072. Specifically, other input devices 4072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here.

[0139] Furthermore, the touch panel 4071 can cover the display panel 4061. When the touch panel 4071 detects a touch operation on or near it, it transmits the information to the processor 410 to determine the type of touch event. Subsequently, the processor 410 provides corresponding visual output on the display panel 4061 based on the type of touch event. Although in Figure 4 In this embodiment, the touch panel 4071 and the display panel 4061 are two independent components to realize the input and output functions of the electronic device. However, in some embodiments, the touch panel 4071 and the display panel 4061 can be integrated to realize the input and output functions of the electronic device. The specific implementation is not limited here.

[0140] Interface unit 408 serves as an interface for connecting external devices to electronic device 400. For example, external devices may include a wired or wireless headphone port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, and so on. Interface unit 406 can be used to receive input from external devices (e.g., data, power, etc.) and transmit the received input to one or more components within electronic device 400, or it can be used to transmit data between electronic device 400 and external devices.

[0141] The memory 409 can be used to store software programs and various data. The memory 409 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback, image playback, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory 409 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0142] The processor 410 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 409, and by calling data stored in the memory 409, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. The processor 410 may include one or more processing units; preferably, the processor 410 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 410.

[0143] The electronic device 400 may also include a power supply 411 (such as a battery) for supplying power to various components. Preferably, the power supply 411 can be logically connected to the processor 410 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system.

[0144] In addition, the electronic device 400 includes some functional modules not shown, which will not be described in detail here.

[0145] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0146] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0147] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

[0148] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0149] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0150] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0151] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0152] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0153] If the aforementioned functions 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, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0154] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for arrears early warning, characterized in that, The method comprises: obtaining the current remaining amount of a user, the monthly package amount, the historical average arrears amount and the remaining days until the next payment; inputting the monthly package amount, the historical average arrears amount and the remaining days until the next payment into an arrears early warning threshold prediction model to obtain an arrears early warning threshold; wherein the arrears early warning threshold prediction model is obtained by training historical arrears related data of the user; the arrears early warning threshold prediction model is a multiple linear regression base model, and the formula is as follows: y = b0 + b1x1 + b2x2 + b3x3 + ε ε is the estimation error of the predicted arrears threshold and the true arrears data, y is the predicted arrears early warning threshold, x1 is the monthly package amount, x2 is the historical average arrears amount, and x3 is the remaining days until the next payment; b0, b1, b2 and b3 are regression parameters to be calculated, b0 is a constant term, the practical significance of b1 is that the higher the monthly package amount, the greater the possibility of arrears of the user; b2 is the historical credit result of the user, which means that the more the historical arrears times, the greater the possibility of arrears this time, so the arrears early warning threshold needs to be improved; b3 is the influence on the possibility of arrears as the payment time is closer; triggering an early warning behavior for the user based on the current remaining amount and the arrears early warning threshold; after inputting the monthly package amount, the historical average arrears amount and the remaining days until the next payment into the arrears early warning threshold prediction model to obtain the arrears early warning threshold, the method further comprises: checking the compliance of the arrears early warning threshold to determine whether the arrears early warning threshold is abnormal; when it is determined that the arrears early warning threshold is abnormal, recording the abnormal arrears early warning threshold through a log; when it is determined that the arrears early warning threshold is normal, performing the step of triggering an early warning behavior for the user based on the current remaining amount and the arrears early warning threshold.

2. The method of claim 1, wherein, obtaining the historical average arrears amount of a user comprises: obtaining the historical total arrears amount and the historical arrears billing period quantity of the user; taking the ratio of the historical total arrears amount to the historical arrears billing period quantity as the historical average arrears amount of the user.

3. The method of claim 1, wherein, The step of triggering an early warning behavior for the user based on the current remaining amount and the arrears early warning threshold comprises: determining whether the current remaining amount is lower than the arrears early warning threshold; if the current remaining amount is lower than or equal to the arrears early warning threshold, triggering an early warning behavior for the user.

4. The method of claim 1, wherein, The early warning behavior for the user at least comprises a short message early warning behavior and a voice early warning behavior.

5. The method of claim 1, wherein, Before inputting the monthly package amount, the historical average arrears amount and the remaining days until the next payment into the arrears early warning threshold prediction model, the method further comprises: obtaining historical arrears related data of the user, the historical arrears related data comprising historical monthly package amount, historical arrears amount, historical arrears billing period quantity and historical payment time; training the arrears early warning threshold prediction model to be trained according to the historical arrears related data to obtain a trained arrears early warning threshold prediction model.

6. The method of claim 1, wherein, after triggering the early warning behavior for the user based on the current remaining amount and the arrearage early warning threshold, further comprising: obtaining the current month arrearage amount of the user; training the arrearage early warning threshold prediction model through the current month arrearage amount, the historical average arrearage amount, the current month package amount, and the remaining days to the next payment deadline to obtain the optimized arrearage early warning threshold prediction model.

7. An arrears early warning device, characterized by, comprising: a data acquisition module configured to acquire the current remaining amount, the current month package amount, the historical average arrearage amount, and the remaining days to the next payment deadline of the user; an early warning threshold prediction module configured to input the current month package amount, the historical average arrearage amount, and the remaining days to the next payment deadline into an arrearage early warning threshold prediction model to obtain an arrearage early warning threshold, wherein the arrearage early warning threshold prediction model is trained through historical arrearage related data of the user, and the arrearage early warning threshold prediction model is a multiple linear regression based model, and a formula of the arrearage early warning threshold prediction model is as follows: y = b0 + b1x1 + b2x2 + b3x3 + ε ε is an estimation error of the predicted arrearage threshold and the real arrearage data, y is the predicted arrearage early warning threshold, x1 is the current month package amount, x2 is the historical average arrearage amount, and x3 is the remaining days to the next payment deadline; b0, b1, b2, and b3 are regression parameters to be calculated, b0 is a constant term, the practical significance of b1 is that the higher the monthly package amount, the greater the possibility of arrearage of the user; b2 is the historical credit result of the user, which indicates that the more the historical arrearage times, the greater the possibility of arrearage this time, and thus the arrearage early warning threshold needs to be improved; and b3 is the influence on the possibility of arrearage when the time to the next payment deadline is closer; an early warning behavior triggering module configured to trigger an early warning behavior for the user based on the current remaining amount and the arrearage early warning threshold; wherein the device further comprises: a threshold checking module configured to check the compliance of the arrearage early warning threshold to determine whether the arrearage early warning threshold is abnormal; a threshold recording module configured to record the abnormal arrearage early warning threshold through a log when it is determined that the arrearage early warning threshold is abnormal; an early warning execution module configured to execute the early warning behavior triggering module when it is determined that the arrearage early warning threshold is normal.

8. An electronic device, comprising: comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete communication among each other through the communication bus; the memory is used to store a computer program; the processor is used to execute the program stored on the memory to implement the method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, instructions stored thereon that, when executed by one or more processors, cause the processors to perform the method of any one of claims 1-6.

Images