A method for predicting balance of an electric energy meter and reminding payment based on time sequence characteristics

Abstract

The embodiment of the specification discloses a power meter balance prediction and payment reminding method based on timing characteristics, which comprises the following steps: acquiring user basic data and historical power consumption data, extracting time characteristics and habit characteristics based on the user basic data and the historical power consumption data; taking the user basic data and the historical power consumption data as training samples, taking the time characteristics and the habit characteristics as input variables, and taking balance use time length as an output variable to train a payment prediction model; collecting the current balance and real-time power consumption data of the user, inputting the current balance and the real-time power consumption data into the payment prediction model to obtain the balance prediction remaining use time length, and reminding the user to pay based on the balance prediction remaining use time length. In this way, the situation of power failure caused by the user's failure to pay in time is avoided, and the user experience is improved.

Description

Technical Field

[0001] This invention relates to the field of prepaid electricity meter management technology, and in particular to a method, device, electronic device and storage medium for predicting electricity meter balance and reminding payment based on time-series characteristics. Background Technology

[0002] In existing technologies, prepaid electricity meters typically use a simple fixed threshold trigger mode for balance reminders. This means that only a single or fixed balance threshold is set (such as 10 yuan or 20 yuan remaining). When the balance falls below this threshold, a reminder message is pushed through a single channel (usually a local audio-visual alert on the meter). However, in special circumstances (such as a surge in electricity consumption due to air conditioning in summer or heating in winter), users' electricity consumption may be high, leading to delayed reminders and power outages caused by users not paying on time. Summary of the Invention

[0003] To address the problems existing in the prior art, this specification describes a method, apparatus, electronic device, and storage medium for predicting electricity meter balance and providing payment reminders based on time-series characteristics through one or more embodiments.

[0004] According to the first aspect, a method for predicting electricity meter balance and reminding payment based on time-series features is provided. The method includes: acquiring user basic data and historical electricity consumption data; extracting time features and habit features based on the user basic data and historical electricity consumption data; the time features are used to represent the user's electricity consumption in different seasons and different time periods; and the habit features are used to represent the user's payment habits.

[0005] A payment prediction model is trained using the user basic data and the historical electricity consumption data as training samples, the time features and the habit features as input variables, and the balance usage duration as the output variable.

[0006] Collect the user's current balance and real-time electricity consumption data, input the user's current balance and real-time electricity consumption data into the payment prediction model to obtain the remaining usage time predicted by the balance, and remind the user to pay the bill based on the remaining usage time predicted by the balance.

[0007] Preferably, the method further includes: obtaining the actual remaining usage time of the balance; if the absolute value of the difference between the predicted remaining usage time of the balance and the actual remaining usage time of the balance is greater than a set difference threshold, obtaining the user basic data and the historical electricity consumption data within the balance usage period, and updating the payment prediction model based on the user basic data and the historical electricity consumption data within the balance usage period.

[0008] Preferably, the step of reminding users to pay based on the remaining usage time predicted by the balance includes: setting at least one payment reminder time based on the remaining usage time predicted by the balance, obtaining a user profile, selecting a payment reminder channel based on the user profile, and sending payment reminder information based on the payment reminder time and the user payment reminder channel.

[0009] Preferably, the method further includes: generating payment reminder optimization data when the user's balance is exhausted due to failure to pay as reminded, and updating the user profile based on the payment reminder optimization data.

[0010] Preferably, the payment reminder information includes the user's current balance, the estimated remaining usage time based on the balance, the recommended payment amount, and the payment channel entry point.

[0011] Preferably, the method further includes: collecting weather correction data and inputting the weather correction data into the payment prediction model to obtain the remaining usage time of the balance prediction.

[0012] Preferably, the payment prediction model outputs the user's daily balance over a period of time, and the step of inputting the weather correction data into the payment prediction model to obtain the remaining usage time of the balance prediction includes: calculating the additional electricity consumption corresponding to each day based on the weather correction data, and calculating the remaining usage time of the balance prediction based on the additional electricity consumption corresponding to each day and the output of the payment prediction model.

[0013] According to the second aspect, a device for predicting and reminding electricity meter balances based on time-series characteristics is provided, the device comprising:

[0014] The feature extraction module is used to obtain user basic data and historical electricity consumption data, and extract time features and habit features based on the user basic data and historical electricity consumption data. The time features are used to represent the user's electricity consumption in different seasons and different time periods, and the habit features are used to represent the user's payment habits.

[0015] The model training module is used to train a payment prediction model by using the user basic data and the historical electricity consumption data as training samples, the time features and the habit features as input variables, and the balance usage duration as the output variable.

[0016] The payment prediction module is used to collect the user's current balance and real-time electricity consumption data, input the user's current balance and real-time electricity consumption data into the payment prediction model to obtain the remaining usage time predicted by the balance, and remind the user to pay based on the remaining usage time predicted by the balance.

[0017] According to a third aspect, an electronic device is provided, including a processor and a memory;

[0018] The processor is connected to the memory;

[0019] The memory is used to store executable program code;

[0020] The processor runs a program corresponding to the executable program code stored in the memory to perform the steps of the method provided as in the first aspect or any possible implementation thereof.

[0021] According to a fourth aspect, a computer-readable storage medium is provided having a computer program stored thereon, the computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform the method provided as in the first aspect or any possible implementation thereof.

[0022] The beneficial effects of this invention are as follows:

[0023] 1. The method and apparatus provided in the embodiments of this specification predict the remaining usage time of a user's balance based on the user's historical electricity consumption habits and seasonal electricity consumption fluctuations, and remind the user based on the predicted remaining usage time of the user's balance, thereby avoiding power outages caused by the user's failure to pay on time and improving the user experience;

[0024] 2. The method and apparatus provided in the embodiments of this specification can update the payment prediction model when the absolute value of the difference between the predicted remaining usage time and the actual remaining usage time is greater than a set difference threshold. This can adapt to changes in user electricity consumption behavior and seasonal fluctuations without manual intervention, reduce the operation and maintenance costs of power companies, and save computing power by setting a difference threshold to avoid frequent model updates.

[0025] 3. The methods and devices provided in the embodiments of this specification select reminder channels according to users' personalized habits and set up multi-level reminders to ensure that users can receive payment reminder information, thereby avoiding power outages caused by users' failure to pay on time and improving the user experience;

[0026] 4. The methods and apparatus provided in the embodiments of this specification introduce weather correction data to re-estimate daily electricity consumption, enabling the billing forecast model to keenly capture load fluctuations caused by sudden weather changes and significantly improve the forecasting accuracy of the billing forecast model. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart illustrating a method for predicting electricity meter balances and providing payment reminders based on time-series characteristics, as implemented in this manual.

[0029] Figure 2 This is a schematic diagram of a time-series-based electricity meter balance prediction and payment reminder device implemented in this specification.

[0030] Figure 3 This is a schematic diagram of the structure of an electronic device used in a specific implementation of this specification. Detailed Implementation

[0031] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0032] In the following description, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The following description provides multiple embodiments of this application, which can be substituted or combined with each other. Therefore, this application can also be considered to include all possible combinations of the same and / or different embodiments described. Thus, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then this application should also be considered to include embodiments containing one or more other possible combinations of A, B, C, and D, even if such embodiments are not explicitly described in the following text.

[0033] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the described elements without departing from the scope of this application. Various processes or components may be appropriately omitted, substituted, or added to the examples. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined into other examples.

[0034] See Figure 1 , Figure 1 This is a flowchart illustrating the method for predicting electricity meter balance and providing payment reminders based on time-series characteristics provided in this application embodiment. In this application embodiment, the method includes:

[0035] S101. Obtain user basic data and historical electricity consumption data, and extract time features and habit features based on the user basic data and historical electricity consumption data. The time features are used to represent the user's electricity consumption in different seasons and different time periods, and the habit features are used to represent the user's payment habits.

[0036] S102. Using the user basic data and the historical electricity consumption data as training samples, the time features and the habit features as input variables, and the balance usage duration as the output variable, a payment prediction model is trained to obtain the payment prediction model.

[0037] S103. Collect the user's current balance and real-time electricity consumption data, input the user's current balance and real-time electricity consumption data into the payment prediction model to obtain the remaining usage time predicted by the balance, and remind the user to pay based on the remaining usage time predicted by the balance.

[0038] The entity executing this application may be a cloud server.

[0039] In the embodiments of this specification, user basic data and historical electricity consumption data are acquired. User basic data includes user type (such as residential, industrial, and commercial), electrical equipment, power of the corresponding equipment, and payment habits (such as payment cycle and payment amount). Historical electricity consumption data refers to recent electricity consumption data, such as electricity consumption data for the past 1-3 years (peak / flat / valley periods), monthly / quarterly electricity consumption data, and electricity consumption fluctuation data for different seasons. Then, feature extraction is performed on the user basic data and historical electricity consumption data to obtain time features and habit features. Time features are used to represent the user's electricity consumption in different seasons and time periods, such as peak electricity consumption in summer and winter, stable electricity consumption in spring and autumn, and the proportion of electricity consumption during peak (7:00-11:00, 17:00-21:00), flat (11:00-17:00), and valley (21:00-7:00 the next day) periods. Habit features are used to represent the user's payment habits, such as the user's habitual payment cycle being 1 month. Then, using user basic data and historical electricity consumption data as training samples, time features and habit features as input variables, and remaining balance usage time as output variable, a payment prediction model is trained through a neural network model (such as RNN, LSTM, GRU, or Transformer time series models) to obtain the payment prediction model. The payment prediction model will output the user's daily balance for a future period. Real-time collection of the user's current balance and real-time electricity consumption data, inputting these into the payment prediction model, yields the predicted remaining usage time. Based on the predicted remaining usage time, payment reminders are sent to the user. This application predicts the user's remaining balance usage time based on historical electricity consumption habits and seasonal electricity fluctuations, and sends reminders to the user based on the predicted remaining usage time, thereby avoiding power outages caused by unpaid bills and improving the user experience.

[0040] In one possible implementation, the method further includes: obtaining the actual remaining usage time of the balance; if the absolute value of the difference between the predicted remaining usage time of the balance and the actual remaining usage time of the balance is greater than a set difference threshold, obtaining the user basic data and the historical electricity consumption data within the balance usage period, and updating the payment prediction model based on the user basic data and the historical electricity consumption data within the balance usage period.

[0041] In the embodiments of this application, after calculating the predicted remaining usage time, the user's balance is monitored in real time to obtain the actual remaining usage time. If the absolute value of the difference between the predicted remaining usage time and the actual remaining usage time is greater than a set difference threshold (e.g., the difference exceeds 5% of the predicted remaining usage time), the user's electricity consumption data during the actual remaining usage time is sent to the cloud server. That is, the user's basic data and historical electricity consumption data during the actual remaining usage time are used as training samples, with time features and habit features as input variables, and the remaining usage time as the output variable. The model is updated through a neural network model (such as RNN, LSTM, GRU, or Transformer time series models) to obtain the updated payment prediction model. This application updates the payment prediction model when the absolute value of the difference between the predicted remaining usage time and the actual remaining usage time exceeds a set difference threshold. This allows the model to adapt to changes in user electricity consumption behavior and seasonal fluctuations without manual intervention, reducing the power company's operation and maintenance costs. Furthermore, by setting a difference threshold, the model update frequency is reduced, thus saving computing power.

[0042] In one possible implementation, the step of reminding users to pay fees based on the predicted remaining usage time of the balance includes: setting at least one payment reminder time based on the predicted remaining usage time of the balance, obtaining a user profile, selecting a user payment reminder channel based on the user profile, and sending payment reminder information based on the payment reminder time and the user payment reminder channel.

[0043] In the embodiments of this application, the cloud server receives feedback information from user reminders, thereby statistically analyzing which channels the user historically used to activate reminders or complete payment operations. It also calculates the time difference between "the system issuing a reminder" and "the user taking action (such as clicking, viewing, or paying)," thus obtaining a user profile, i.e., the priority of each reminder channel. Reminder channels include SMS, App push notifications, WeChat official account / mini-program template messages, email (EDM), telephone voice calls, and smartwatch notifications, etc. At least one payment reminder time is generated based on the remaining usage time predicted by the balance, such as setting three levels of reminder thresholds: Level 1 reminder (7-10 days of remaining balance), Level 2 reminder (3-6 days of remaining balance), and Level 3 reminder (1-2 days of remaining balance). At the payment reminder time, based on the obtained user profile and the current scenario (e.g., if the user's phone is online, the App is prioritized; if the phone is offline, SMS + voice is prioritized; if the user is near the meter, local display is triggered), the optimal reminder channel is automatically selected, and the payment reminder information is sent. This application selects reminder channels tailored to users' personalized habits and sets up multi-level reminders to ensure that users receive payment reminders, thereby preventing power outages caused by users' failure to pay on time and improving the user experience.

[0044] In one possible implementation, the method further includes: generating payment reminder optimization data when a user fails to pay as reminded, resulting in the user's balance being exhausted, and updating the user profile based on the payment reminder optimization data.

[0045] In the embodiments of this application, if a user fails to pay as reminded, resulting in the depletion of their balance, the reminder channel and the user are recorded, and a reminder failure label is added. The information indicating the reminder channel and the user, along with the reminder failure label corresponding to the above information, is sent to the cloud server. Based on this information, the cloud server lowers the priority of the reminder channel, thereby optimizing the selection of subsequent channels.

[0046] In one possible implementation, the payment reminder information includes the user's current balance, the estimated remaining usage time of the balance, the recommended payment amount, and the payment channel entry point.

[0047] In the embodiments of this application, the payment reminder information includes the user's current balance, the estimated remaining usage time, the recommended payment amount, and the payment channel entry point, making it convenient for users to pay quickly.

[0048] In one possible implementation, the method further includes: collecting weather correction data and inputting the weather correction data into the payment prediction model to obtain the remaining usage time of the balance prediction.

[0049] In the embodiments of this application, as described above, rainy or snowy weather can also affect users' electricity consumption. For example, cooler summer rainy days lead to lower electricity consumption. To ensure the prediction accuracy of the payment forecasting model, weather correction data is collected, including temperature and humidity. First, based on the aforementioned time characteristics, such as the "summer" label, a basic electricity consumption curve is given (e.g., an estimated average hourly electricity consumption of 5 kWh). Current and future weather correction data are introduced, such as a temperature of 38°C. The electricity consumption for the day is added to the additional electricity consumption caused by the weather correction data. Then, based on the user's daily balance for a future period output by the payment forecasting model and the additional electricity consumption caused by the weather correction data, the remaining usage time is recalculated to predict the remaining balance. In this application, weather correction data is introduced to re-estimate daily electricity consumption, enabling the payment forecasting model to accurately capture load fluctuations caused by sudden weather changes, significantly improving the prediction accuracy of the payment forecasting model.

[0050] The following will be combined with the appendix Figure 2 This paper provides a detailed description of the electricity meter balance prediction and payment reminder device based on time-series characteristics provided in the embodiments of this application. It should be noted that the appendix... Figure 2 The time-series-based electricity meter balance prediction and payment reminder device shown is used to perform the functions described in this application. Figure 1 The methods shown in the embodiments are for illustrative purposes only, illustrating the parts relevant to the embodiments of this application. For specific technical details not disclosed, please refer to this application. Figure 1 The example shown.

[0051] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of the electricity meter balance prediction and payment reminder device based on time-series characteristics provided in the embodiments of this application. Figure 2 As shown, the device includes:

[0052] The feature extraction module 201 is used to obtain user basic data and historical electricity consumption data, and extract time features and habit features based on the user basic data and historical electricity consumption data. The time features are used to represent the user's electricity consumption in different seasons and different time periods, and the habit features are used to represent the user's payment habits.

[0053] The model training module 202 is used to train a payment prediction model by using the user basic data and the historical electricity consumption data as training samples, the time features and the habit features as input variables, and the balance usage duration as the output variable.

[0054] The payment prediction module 203 is used to collect the user's current balance and real-time electricity consumption data, input the user's current balance and real-time electricity consumption data into the payment prediction model to obtain the remaining usage time predicted by the balance, and remind the user to pay based on the remaining usage time predicted by the balance.

[0055] In one possible implementation, the model training module 202 is specifically used for:

[0056] Obtain the actual remaining usage time of the balance. If the absolute value of the difference between the predicted remaining usage time of the balance and the actual remaining usage time of the balance is greater than a set difference threshold, obtain the user's basic data and the historical electricity consumption data within the balance usage period, and update the payment prediction model based on the user's basic data and the historical electricity consumption data within the balance usage period.

[0057] In one possible implementation, the payment prediction module 203 is specifically used for:

[0058] Based on the remaining usage time predicted by the balance, at least one payment reminder time is set, a user profile is obtained, a user payment reminder channel is selected based on the user profile, and a payment reminder message is sent based on the payment reminder time and the user payment reminder channel.

[0059] In one possible implementation, the payment prediction module 203 is specifically used for:

[0060] When a user fails to pay their bill as reminded, resulting in the depletion of their balance, payment reminder optimization data is generated, and the user profile is updated based on the payment reminder optimization data.

[0061] In one possible implementation, the payment prediction module 203 is specifically used for:

[0062] The payment reminder information includes the user's current balance, the estimated remaining usage time based on the balance, the recommended payment amount, and the payment channel entry point.

[0063] In one possible implementation, the payment prediction module 203 is specifically used for:

[0064] Collect weather correction data and input the weather correction data into the payment prediction model to obtain the remaining usage time of the balance prediction.

[0065] In one possible implementation, the payment prediction module 203 is specifically used for:

[0066] The payment prediction model outputs the user's daily balance over a period of time. The step of inputting the weather correction data into the payment prediction model to obtain the remaining usage time of the balance prediction includes: calculating the additional electricity consumption corresponding to each day based on the weather correction data, and calculating the remaining usage time of the balance prediction based on the additional electricity consumption corresponding to each day and the output of the payment prediction model.

[0067] Those skilled in the art will clearly understand that the technical solutions of the embodiments of this application can be implemented by means of software and / or hardware. In this specification, "unit" and "module" refer to software and / or hardware that can independently complete or cooperate with other components to complete a specific function, wherein the hardware may be, for example, a field-programmable gate array (FPGA), an integrated circuit (IC), etc.

[0068] Each processing unit and / or module in the embodiments of this application can be implemented by an analog circuit that implements the functions described in the embodiments of this application, or by software that executes the functions described in the embodiments of this application.

[0069] See Figure 3 It shows a schematic diagram of the structure of an electronic device according to an embodiment of this application, which can be used to implement... Figure 1 The method in the illustrated embodiment. (As shown) Figure 3 As shown, the electronic device 300 may include: at least one central processing unit 301, at least one network interface 304, user interface 303, memory 305, and at least one communication bus 302.

[0070] The communication bus 302 is used to enable communication between these components.

[0071] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0072] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0073] The central processing unit 301 may include one or more processing cores. The central processing unit 301 connects to various parts within the electronic device 300 using various interfaces and lines. It executes various functions of the terminal 300 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305. Optionally, the central processing unit 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The central processing unit 301 may integrate one or more of the following: a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the central processing unit 301.

[0074] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned central processing unit 301. Figure 3 As shown, the memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and program instructions.

[0075] exist Figure 3In the illustrated electronic device 300, the user interface 303 is mainly used to provide an input interface for the user and to acquire user input data; while the central processing unit 301 can be used to call the application program stored in the memory 305 and specifically perform the following operations:

[0076] S101. Obtain user basic data and historical electricity consumption data, and extract time features and habit features based on the user basic data and historical electricity consumption data. The time features are used to represent the user's electricity consumption in different seasons and different time periods, and the habit features are used to represent the user's payment habits.

[0077] S102. Using the user basic data and the historical electricity consumption data as training samples, the time features and the habit features as input variables, and the balance usage duration as the output variable, a payment prediction model is trained to obtain the payment prediction model.

[0078] S103. Collect the user's current balance and real-time electricity consumption data, input the user's current balance and real-time electricity consumption data into the payment prediction model to obtain the remaining usage time predicted by the balance, and remind the user to pay based on the remaining usage time predicted by the balance.

[0079] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0080] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0081] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed apparatus 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 service interface; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0083] 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.

[0084] Furthermore, the functional units in the various embodiments of this application 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0085] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 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 application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0086] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0087] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of embodiments of this disclosure upon considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for predicting electricity meter balance and providing payment reminders based on time-series characteristics, characterized in that, The method includes: Acquire basic user data and historical electricity consumption data, and extract time features and habit features based on the basic user data and historical electricity consumption data. The time features are used to represent the user's electricity consumption in different seasons and different time periods, and the habit features are used to represent the user's payment habits. A payment prediction model is trained using the user basic data and the historical electricity consumption data as training samples, the time features and the habit features as input variables, and the balance usage duration as the output variable. Collect the user's current balance and real-time electricity consumption data, input the user's current balance and real-time electricity consumption data into the payment prediction model to obtain the remaining usage time predicted by the balance, and remind the user to pay the bill based on the remaining usage time predicted by the balance.

2. The method for predicting electricity meter balance and providing payment reminders based on time-series characteristics according to claim 1, characterized in that, The method further includes: obtaining the actual remaining usage time of the balance; if the absolute value of the difference between the predicted remaining usage time of the balance and the actual remaining usage time of the balance is greater than a set difference threshold, obtaining the user basic data and the historical electricity consumption data within the balance usage period, and updating the payment prediction model based on the user basic data and the historical electricity consumption data within the balance usage period.

3. The method for predicting electricity meter balance and providing payment reminders based on time-series characteristics according to claim 1, characterized in that, The step of reminding users to pay fees based on the remaining usage time predicted by the balance includes: setting at least one payment reminder time based on the remaining usage time predicted by the balance, obtaining a user profile, selecting a payment reminder channel based on the user profile, and sending payment reminder information based on the payment reminder time and the user payment reminder channel.

4. The method for predicting electricity meter balance and providing payment reminders based on time-series characteristics according to claim 3, characterized in that, The method further includes: generating payment reminder optimization data when a user fails to pay as reminded, resulting in the user's balance being exhausted, and updating the user profile based on the payment reminder optimization data.

5. The method for predicting electricity meter balance and providing payment reminders based on time-series characteristics according to claim 3, characterized in that, The payment reminder information includes the user's current balance, the estimated remaining usage time based on the balance, the recommended payment amount, and the payment channel entry point.

6. The method for predicting electricity meter balance and providing payment reminders based on time-series characteristics according to claim 1, characterized in that, The method further includes: collecting weather correction data and inputting the weather correction data into the payment prediction model to obtain the remaining usage time of the balance prediction.

7. The method for predicting electricity meter balance and providing payment reminders based on time-series characteristics according to claim 6, characterized in that, The payment prediction model outputs the user's daily balance over a period of time. The step of inputting the weather correction data into the payment prediction model to obtain the remaining usage time of the balance prediction includes: calculating the additional electricity consumption corresponding to each day based on the weather correction data, and calculating the remaining usage time of the balance prediction based on the additional electricity consumption corresponding to each day and the output of the payment prediction model.

8. A device for predicting electricity meter balance and reminding payment based on time-series characteristics, characterized in that, The apparatus implements the steps of the method as described in any one of claims 1-7, the apparatus comprising: The feature extraction module is used to obtain user basic data and historical electricity consumption data, and extract time features and habit features based on the user basic data and historical electricity consumption data. The time features are used to represent the user's electricity consumption in different seasons and different time periods, and the habit features are used to represent the user's payment habits. The model training module is used to train a payment prediction model by using the user basic data and the historical electricity consumption data as training samples, the time features and the habit features as input variables, and the balance usage duration as the output variable. The payment prediction module is used to collect the user's current balance and real-time electricity consumption data, input the user's current balance and real-time electricity consumption data into the payment prediction model to obtain the remaining usage time predicted by the balance, and remind the user to pay based on the remaining usage time predicted by the balance.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, the computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform the steps of the method as claimed in any one of claims 1-7.

Images