Online payment information reminding method and system

Abstract

The invention provides an online payment information reminding method and system, and relates to the technical field of online payment information reminding, and the method comprises the steps: obtaining a video shot by a camera of a shopping crowd; based on the video shot by the camera of the shopping crowd, using a generative adversarial network to generate a subsequent payment video of the shopping crowd; determining a plurality of payment time periods and the number of payment information of each payment time period by using a payment processing model based on the subsequent payment video of the shopping crowd; determining the broadcasting speed of each payment time period based on the plurality of payment time periods and the number of the payment information of each payment time period; and performing data reminding based on the broadcast speed of each payment time period. The method can accurately determine the broadcast speed of each payment time period.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of online payment information reminding, in particular to an online payment information reminding method and system. BACKGROUND

[0002] In the retail payment scenario, how to dynamically adjust the broadcast speed according to the amount of payment information in different payment time periods is a key problem to improve the efficiency of payment information broadcast and user experience. The existing voice broadcast system usually uses a fixed broadcast frequency, which cannot be flexibly adjusted according to the actual amount of information in each payment time period. For example, in a payment time period, the concentrated payment behavior of the shopping crowd may cause the amount of payment information to increase significantly, but due to the failure to adjust the broadcast speed in time, multiple messages may be broadcast at the same time, causing message coverage or omission and affecting the user's reception of payment information. In addition, the existing method relies mainly on historical payment data and lacks dynamic sensing ability for the actual behavior of the shopping crowd, making it difficult to accurately capture the information amount changes in different payment time periods.

[0003] Therefore, how to accurately determine the broadcast speed of each payment time period is a problem to be solved at present. SUMMARY

[0004] The technical problem solved by the present application is how to accurately determine the broadcast speed of each payment time period.

[0005] According to a first aspect, the present application provides an online payment information reminding method, comprising: acquiring a camera shooting video of a shopping crowd; generating a subsequent payment video of the shopping crowd using a generative adversarial network based on the camera shooting video of the shopping crowd; determining a plurality of payment time periods and the number of payment information in each payment time period using a payment processing model based on the subsequent payment video of the shopping crowd; determining the broadcast speed of each payment time period based on the plurality of payment time periods and the number of payment information in each payment time period; and performing data reminding based on the broadcast speed of each payment time period.

[0006] In one possible implementation, the determination of the broadcast speed of each payment time period based on the plurality of payment time periods and the number of payment information in each payment time period comprises: constructing a knowledge graph, the knowledge graph comprising a plurality of payment time period nodes and a plurality of edges between the plurality of payment time period nodes, each payment time period node being a payment time period, the node features of each payment time period node comprising the number of payment information in each payment time period, and the edges between two payment time period nodes representing the time relationship between the two payment time periods; and determining the broadcast speed of each payment time period based on processing of the knowledge graph by a graph convolution network.

[0007] In a possible implementation, the input of the generative adversarial network is a camera shooting video of the shopping crowd, and the output of the generative adversarial network is a subsequent payment video of the shopping crowd.

[0008] In a possible implementation, the payment processing model is a Transformer model.

[0009] According to a second aspect, the application provides an online payment information reminding system, comprising: an acquisition module configured to acquire a camera shooting video of a shopping crowd; a generation module configured to generate a subsequent payment video of the shopping crowd based on the camera shooting video of the shopping crowd using a generative adversarial network; an information processing module configured to determine a plurality of payment time periods and a number of payment information items in each payment time period based on the subsequent payment video of the shopping crowd using a payment processing model; a broadcast speed determination module configured to determine a broadcast speed of each payment time period based on the plurality of payment time periods and the number of payment information items in each payment time period; and a data reminding module configured to perform data reminding based on the broadcast speed of each payment time period.

[0010] In a possible implementation, the broadcast speed determination module is further configured to: construct a knowledge graph, the knowledge graph comprising a plurality of payment time period nodes and a plurality of edges between the plurality of payment time period nodes, each payment time period node being a payment time period, a node feature of each payment time period node comprising a number of payment information items in each payment time period, and an edge between two payment time period nodes representing a time relationship between the two payment time periods; and determine the broadcast speed of each payment time period by processing the knowledge graph based on a graph convolution network.

[0011] In a possible implementation, the input of the generative adversarial network is a camera shooting video of the shopping crowd, and the output of the generative adversarial network is a subsequent payment video of the shopping crowd.

[0012] In a possible implementation, the payment processing model is a Transformer model.

[0013] According to a third aspect, embodiments of the present application provide an electronic device, comprising: a processor; a memory; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above, the method comprising: obtaining a camera shooting video of a shopping crowd; generating a subsequent payment video of the shopping crowd based on the camera shooting video of the shopping crowd using a generative adversarial network; determining a plurality of payment time periods, a number of payment information pieces of each payment time period based on the subsequent payment video of the shopping crowd using a payment processing model; determining a broadcast speed of each payment time period based on the plurality of payment time periods and the number of payment information pieces of each payment time period; and performing data prompting based on the broadcast speed of each payment time period.

[0014] According to a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the online payment information prompting method as described above, the method comprising: obtaining a camera shooting video of a shopping crowd; generating a subsequent payment video of the shopping crowd based on the camera shooting video of the shopping crowd using a generative adversarial network; determining a plurality of payment time periods, a number of payment information pieces of each payment time period based on the subsequent payment video of the shopping crowd using a payment processing model; determining a broadcast speed of each payment time period based on the plurality of payment time periods and the number of payment information pieces of each payment time period; and performing data prompting based on the broadcast speed of each payment time period.

[0015] The present application provides an online payment information prompting method and system, the method comprising: obtaining a camera shooting video of a shopping crowd; generating a subsequent payment video of the shopping crowd based on the camera shooting video of the shopping crowd using a generative adversarial network; determining a plurality of payment time periods, a number of payment information pieces of each payment time period based on the subsequent payment video of the shopping crowd using a payment processing model; determining a broadcast speed of each payment time period based on the plurality of payment time periods and the number of payment information pieces of each payment time period; and performing data prompting based on the broadcast speed of each payment time period, which can accurately determine the broadcast speed of each payment time period. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 An application scenario diagram of the online payment information prompting method provided by the embodiments of the present application is shown in the figure. Figure 2 A flowchart of the online payment information prompting method provided by the embodiments of the present application is shown in the figure. Figure 3 A flowchart of determining the broadcast speed of each payment time period provided by the embodiments of the present application is shown in the figure. Figure 4This is a schematic diagram of an online payment information reminder system provided in an embodiment of the present invention; Figure 5 A schematic diagram of an electronic device provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0017] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the invention. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present invention are not shown or described in the specification. This is to avoid obscuring the core parts of the invention with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0018] Figure 1 This is a schematic diagram illustrating an application scenario of an online payment information reminder method provided in an embodiment of the present invention. Figure 1 The application scenarios for online payment information reminder methods can include servers 11, networks 12, terminals 13, and storage devices 14.

[0019] In some embodiments, server 11 may be a single server or a group of servers. Server 11 can access information and / or data stored in terminal 13 or storage device 14 via network 12. In some embodiments, server 11 may be used to perform... Figure 2 The online payment information notification method is shown in the figure.

[0020] Network 12 can facilitate the exchange of information and / or data. In some embodiments, network 12 can be any form of wired or wireless network, or any combination thereof.

[0021] Terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, terminal 13 may include one or more combinations of mobile devices, tablet computers, laptop computers, etc.

[0022] Storage device 14 can store data and / or instructions, for example, storage device 14 can store data instructions for online payment information reminder methods.

[0023] In this embodiment of the invention, the following are provided: Figure 2The above describes an online payment information reminder method, which includes steps S1 to S5: Step S1: Obtain video footage captured by cameras from the shopping crowd; Shoppers are groups of consumers who engage in shopping activities at specific locations. They typically gather in key areas such as payment areas, product display areas, or promotional areas to select goods and make payments.

[0024] Video recording of shoppers by cameras refers to video data captured by cameras showing the behavior of shoppers within a specific area. This video data can reflect patterns in shoppers' activity and concentrated behaviors. In some embodiments, cameras can be installed in shopping areas to capture the movement and behavior of shoppers in real time.

[0025] Step S2: Based on the video captured by the camera of the shopping crowd, a generative adversarial network is used to generate a subsequent payment video of the shopping crowd; Generative Adversarial Networks (GANs) are deep learning models and a method for implementing artificial intelligence. A GAN consists of a generator and a discriminator. The generator is responsible for generating new data samples, while the discriminator is responsible for distinguishing generated samples from real samples. Through adversarial training, the generator gradually learns to generate realistic data, while the discriminator continuously improves its discrimination ability. The input to the GAN is video footage captured by a camera of the shoppers, and the output is video footage of the shoppers' subsequent payment.

[0026] The subsequent payment videos of shoppers are a set of simulated videos of shoppers' behavior during the payment process, generated by a generative adversarial network. These subsequent payment videos can intuitively demonstrate the behavioral patterns of shoppers during the payment process.

[0027] Generative Adversarial Networks (GANs) are able to generate videos depicting the subsequent payment process of shoppers primarily due to the adversarial mechanism between their generator and discriminator. The generator learns behavioral characteristics of shoppers, such as dwell time and interactive actions, to simulate their behavior during the payment process and generate realistic subsequent payment videos. The discriminator then evaluates the authenticity of the generated video by comparing it with real payment videos and provides feedback to the generator for optimization. Through repeated training, the generator gradually learns to generate videos that highly resemble real payment scenarios.

[0028] Step S3: Based on the subsequent payment videos of the shopping crowd, use the payment processing model to determine multiple payment time periods and the number of payment information items in each payment time period; The payment processing model is a Transformer model. The input of the payment processing model is the subsequent payment video of the shopping crowd. The output of the payment processing model is multiple payment time periods and the number of payment information entries in each payment time period.

[0029] The Transformer model consists of an encoder and a decoder. The encoder learns representations of the input sequence through a self-attention mechanism and a feedforward neural network, capturing global dependencies within the sequence. The decoder generates the target sequence based on the encoder through a multi-head attention mechanism. The Transformer model performs exceptionally well when processing time-series data, capturing long-range dependencies in payment videos, such as the temporal distribution and density of payment actions. This capability allows the Transformer model to efficiently extract key time points and probability distribution sequences of payment actions. The Transformer model can be used to process subsequent payment videos of shoppers, better capturing the temporal relationships within the video.

[0030] Multiple payment time slots are continuous time ranges divided based on the temporal distribution of payment behavior within the payment video. These time slots are determined by analyzing the density and trends of payment behavior within the payment video using an information processing model. For example, in a 5-minute payment video, payment time slots could include 0:00 to 0:30, 0:30 to 1:15, 1:15 to 2:00, and 2:00 to 5:00. Each time slot is an independent payment time slot.

[0031] The number of payment records per payment time period refers to the number of payment transactions that occurred within each defined payment time period. For example, 13 payment transactions occurred between 0:00 and 0:05, and 7 payment transactions occurred between 0:05 and 0:15.

[0032] The core advantage of the Transformer model lies in its ability to efficiently process time-series data and extract key features from subsequent payment videos of shoppers. Through its self-attention mechanism, the Transformer model can efficiently analyze the behavioral patterns of shoppers in video sequences and identify concentrated periods of payment activity. Simultaneously, the Transformer model can combine the time dimension and payment behavior features to accurately segment multiple payment time periods and count the number of payment information entries within each time period. The Transformer model's self-attention mechanism allows it to capture long-term dependencies in video data, thus enabling more accurate analysis of shoppers' payment behavior trends. Furthermore, the Transformer model's multi-head attention mechanism can process different features in the video sequence in parallel, further improving the accuracy of the payment information entry count. This capability allows the Transformer model to extract key information from complex video data, providing a reliable basis for segmenting payment time periods and counting payment information entries.

[0033] In some embodiments, the payment processing model includes an information extraction layer, a segmentation time point determination layer, and an information statistics layer. The input to the information extraction layer is the subsequent payment video of the shoppers, and the output is multiple initial segmentation time points and the payment behavior distribution pattern between adjacent initial segmentation time points. The input to the segmentation time point determination layer is multiple initial segmentation time points and the payment behavior distribution pattern between adjacent initial segmentation time points, and the output is multiple final segmentation time points. The input to the information statistics layer is the subsequent payment video of the shoppers and multiple final segmentation time points, and the output is multiple payment time periods and the number of payment information entries in each payment time period.

[0034] Multiple initial segmentation time points refer to a set of time points initially extracted from the subsequent payment videos of the shopping group.

[0035] The distribution patterns of payment behavior between adjacent initial selection and segmentation time points include distribution patterns and distribution sequences.

[0036] Distribution patterns include uniform distribution, concentrated distribution, and random distribution.

[0037] A distribution sequence is an ordered arrangement of the specific times when payment actions occur within the time interval between adjacent initial selection and segmentation points. By recording the specific times of payment actions on the timeline, the distribution sequence can intuitively reflect the distribution of payment actions between adjacent initial selection and segmentation points.

[0038] By dividing the model into different layers, each layer can focus on performing a specific task. For example, the information extraction layer can focus on extracting multiple initial segmentation time points and the distribution patterns of payment behavior between adjacent initial segmentation time points from payment videos. The segmentation time point determination layer determines multiple final segmentation time points by comprehensively analyzing multiple initial segmentation time points and the distribution patterns of payment behavior between adjacent initial segmentation time points, ensuring the accuracy and rationality of the multiple final segmentation time points. The information statistics layer can identify multiple payment time periods from the subsequent payment videos of the shopping group based on multiple final segmentation time points, and analyze payment behavior to calculate the number of payment information entries in each payment time period. This modular approach allows each layer to be optimized specifically for its task, thereby improving the efficiency and performance of the overall model. By decomposing the task into multiple steps, with each step building upon the previous one, information can be progressively refined and distilled. This method helps improve the accuracy of the final output data because each layer can focus on improving the accuracy of its specific task, thereby improving the reliability of the entire model.

[0039] Step S4: Determine the broadcast speed for each payment time period based on the multiple payment time periods and the number of payment information items in each payment time period.

[0040] In some embodiments, Figure 3 This is a flowchart illustrating the process of determining the broadcast speed for each payment time period, as provided in an embodiment of the present invention. The determination of the broadcast speed for each payment time period includes steps S21-S22: Step S21: Construct a knowledge graph. The knowledge graph includes multiple payment time period nodes and multiple edges between the multiple payment time period nodes. Each payment time period node is a payment time period. The node features of each payment time period node include the number of payment information items in each payment time period. The edge between two payment time period nodes represents the time relationship between the two payment time periods. A knowledge graph is a data structure used to represent entities and their relationships. A knowledge graph consists of vertices and edges. Each node represents a payment time period, and its characteristics include the number of payment information entries within that time period, reflecting the intensity of payment activity. Edges represent the temporal relationship between two payment time periods, such as a chronological order. Through the relationships between edges, the continuity between payment time periods and their potential impact on broadcast speed can be captured. By constructing a knowledge graph, the relationships and characteristics between different payment time periods can be clearly represented.

[0041] Step S22: Process the knowledge graph based on the graph convolutional network to determine the broadcast speed for each payment time period.

[0042] The input to the graph convolutional network is the knowledge graph, and the output of the graph convolutional network is the broadcast speed for each payment time period.

[0043] Graph Convolutional Networks (GCNs) are an implementation of artificial intelligence and a deep learning model specifically designed for processing graph-structured data. Unlike traditional neural networks, GCNs can directly analyze graph-structured data, passing information between nodes through message passing mechanisms to capture complex relationships between them. This characteristic makes GCNs excellent at processing graph data with local connections and global dependencies, and they are particularly suitable for structured data such as knowledge graphs composed of nodes and edges.

[0044] The broadcast rate for each payment time period is determined by a graph convolutional network, which specifies the frequency of payment information broadcast within that time period. Determining the broadcast rate requires comprehensive consideration of the intensity of payment activity within the payment time period and its relationship with adjacent time periods. For example, during peak payment periods, if multiple payment messages are broadcast simultaneously, some messages may be overwritten or unclear. To avoid this, the broadcast frequency needs to be appropriately reduced to ensure that each payment message is broadcast completely. Conversely, during off-peak periods, when there is less payment information, the broadcast frequency can be appropriately increased to maintain system responsiveness. By dynamically adjusting the broadcast rate, it is possible to ensure that payment information is broadcast clearly and completely in different time periods, avoiding message loss or overwriting.

[0045] Graph Convolutional Networks (GCNNs) are effective at processing knowledge graphs due to their unique message-passing mechanism and adaptability to graph-structured data. GCNNs capture complex relationships between nodes by aggregating information from neighboring nodes and updating the feature representation of each node. This mechanism allows GCNNs to comprehensively consider local and global relationships and extract key information from the graph structure. For example, in the context of payment time periods, GCNNs can analyze node features and edge relationships to capture the temporal dependencies and intensity of payment activity between payment time periods. If the number of payment information entries in a payment time period increases significantly, the GCNN will incorporate information from adjacent time periods into its calculations, thereby generating more accurate predictions of broadcast speed. In this way, GCNNs can dynamically adjust the broadcast speed to ensure the efficient operation of the payment system across different time periods.

[0046] Step S5: Provide data reminders based on the broadcast speed of each payment time period.

[0047] Once the broadcast speed for each payment time period is determined, payment information reminders are sent based on the broadcast speed.

[0048] Based on the same inventive concept Figure 4 This is a schematic diagram of an online payment information reminder system provided in an embodiment of the present invention. The online payment information reminder system includes: Module 41 is used to acquire video footage captured by cameras of shoppers; The generation module 42 is used to generate subsequent payment videos of the shoppers using a generative adversarial network based on the video captured by the camera of the shoppers. Information processing module 43 is used to determine multiple payment time periods and the number of payment information items in each payment time period based on the subsequent payment videos of the shopping group using a payment processing model; The broadcast speed determination module 44 is used to determine the broadcast speed of each payment time period based on the multiple payment time periods and the number of payment information items in each payment time period; The data reminder module 45 is used to provide data reminders based on the broadcast speed of each payment time period.

[0049] Based on the same inventive concept, embodiments of the present invention provide an electronic device, such as... Figure 5 As shown, it includes: The system includes: a processor 51; a memory 52; and a computer program; wherein the computer program is stored in the memory 52 and configured to be executed by the processor 51 to implement the online payment information reminder method provided above, the method including: acquiring video footage captured by a camera of a group of shoppers; generating subsequent payment videos of the shoppers using a generative adversarial network based on the camera footage of the shoppers; determining multiple payment time periods and the number of payment information items in each payment time period using a payment processing model based on the subsequent payment videos of the shoppers; determining the broadcast speed of each payment time period based on the multiple payment time periods and the number of payment information items in each payment time period; and providing data reminders based on the broadcast speed of each payment time period.

[0050] Based on the same inventive concept, this embodiment provides a computer-readable storage medium storing a computer program that, when executed by processor 51, implements the aforementioned online payment information reminder method. The method includes: acquiring video footage captured by a camera of shoppers; generating subsequent payment videos of the shoppers using a generative adversarial network based on the camera footage; determining multiple payment time periods and the number of payment information items in each payment time period using a payment processing model based on the subsequent payment videos; determining the playback speed of each payment time period based on the multiple payment time periods and the number of payment information items in each payment time period; and providing data reminders based on the playback speed of each payment time period.

[0051] The online payment information reminder method provided in this application embodiment can be applied to terminal devices (such as mobile phones), tablet computers, laptops, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smartwatches, smart glasses, or smart helmets), augmented reality (AR) / virtual reality (VR) devices, smart home devices, in-vehicle computers, and other electronic devices. This application embodiment does not impose any limitations on this.

[0052] Taking mobile phone 100 as an example of the aforementioned electronic devices, Figure 6 A structural schematic diagram of mobile phone 100 is shown.

[0053] like Figure 6 As shown, the mobile phone 100 may include a processing module 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, buttons 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0054] The processing module 110 can be used to: detect when a user opens a software page, then open the front-facing camera and screen recording; acquire video footage captured by the camera of the shoppers; generate subsequent payment videos of the shoppers using a generative adversarial network based on the video footage captured by the camera of the shoppers; determine multiple payment time periods and the number of payment information items in each payment time period using a payment processing model based on the subsequent payment videos of the shoppers; determine the broadcast speed of each payment time period based on the multiple payment time periods and the number of payment information items in each payment time period; and provide data reminders based on the broadcast speed of each payment time period.

[0055] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0056] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for online payment information reminders, characterized in that, include: Obtain video footage from cameras of shoppers; Based on the video footage captured by the cameras of the shoppers, a generative adversarial network is used to generate subsequent payment videos of the shoppers. Based on the subsequent payment videos of the aforementioned shopping group, a payment processing model is used to determine multiple payment time periods and the number of payment information entries in each payment time period; The broadcast speed for each payment time period is determined based on the multiple payment time periods and the number of payment information items in each payment time period; Data reminders are provided based on the broadcast speed for each payment time period.

2. The online payment information reminder method as described in claim 1, characterized in that, The method of determining the broadcast speed for each payment time period based on the multiple payment time periods and the number of payment information items in each payment time period includes: A knowledge graph is constructed, which includes multiple payment time period nodes and multiple edges between the multiple payment time period nodes. Each payment time period node is a payment time period. The node features of each payment time period node include the number of payment information items in each payment time period. The edge between two payment time period nodes represents the time relationship between the two payment time periods. The knowledge graph is processed using graph convolutional networks to determine the broadcast speed for each payment time period.

3. The online payment information reminder method as described in claim 1, characterized in that, The input to the generative adversarial network is video footage captured by cameras of the shoppers, and the output of the generative adversarial network is video footage of the shoppers making subsequent payments.

4. The online payment information reminder method as described in claim 1, characterized in that, The payment processing model is the Transformer model.

5. An online payment information reminder system, characterized in that, include: The acquisition module is used to acquire video footage captured by cameras of shoppers; The generation module is used to generate subsequent payment videos of the shoppers using a generative adversarial network based on the video captured by the camera of the shoppers; The information processing module is used to determine multiple payment time periods and the number of payment information entries in each payment time period based on the subsequent payment videos of the shopping group using a payment processing model; The broadcast speed determination module is used to determine the broadcast speed of each payment time period based on the multiple payment time periods and the number of payment information items in each payment time period; The data alert module is used to provide data alerts based on the broadcast speed of each payment time period.

6. The online payment information reminder system as described in claim 5, characterized in that, The broadcast speed determination module is also used for: A knowledge graph is constructed, which includes multiple payment time period nodes and multiple edges between the multiple payment time period nodes. Each payment time period node is a payment time period. The node features of each payment time period node include the number of payment information items in each payment time period. The edge between two payment time period nodes represents the time relationship between the two payment time periods. The knowledge graph is processed using graph convolutional networks to determine the broadcast speed for each payment time period.

7. The online payment information reminder system as described in claim 5, characterized in that, The input to the generative adversarial network is video footage captured by cameras of the shoppers, and the output of the generative adversarial network is video footage of the shoppers making subsequent payments.

8. The online payment information reminder system as described in claim 5, characterized in that, The payment processing model is the Transformer model.

9. An electronic device, characterized in that, include: processor; Memory; And a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the online payment information reminder method as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the online payment information reminder method as described in any one of claims 1 to 4.

Images