A method, device and product for sharing a traffic package balance warning

Abstract

The application provides a shared traffic package remaining amount early warning method and device and products, wherein the method comprises: inputting first historical data of a plurality of first IPs using a shared traffic resource in a first preset time length as input into a previously obtained traffic analysis prediction model to obtain a first predicted consumption traffic value of the first IPs in a second preset time length after a current time; performing traffic simulation deduction in current traffic of at least one shared traffic package in the shared traffic resource according to the first predicted consumption traffic value to obtain remaining traffic of the current traffic after the traffic simulation deduction; and performing traffic warning prompt in the case that the remaining traffic is less than a first threshold. The shared traffic packages of different resource pools are uniformly simulated and deducted, and warning is performed when the current traffic is not enough for deduction, which can prompt the user to supplement new shared traffic packages in advance, thereby avoiding the problem of traffic package remaining amount warning failure, skipping warning, and directly generating traffic charges.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a method, device, and product for predicting the remaining capacity of shared data packets. Background Technology

[0002] Currently, a large portion of public clouds lacks a shared traffic package balance alert solution; only a limited number of shared traffic packages currently offer this feature. One type of shared traffic package doesn't differentiate between resource pools but is categorized by geographical region (Asia Pacific and Europe / America) and by time (full-time and off-time). The shared traffic package balance alert function can be configured simply by combining regional and time-based settings. It calculates the total amount of shared traffic packages held and the balance ratio; if the balance falls below a threshold, an alert is triggered. However, for other public cloud shared traffic packages, the available balance across different resource pools at the same time varies, leading to situations where balance alerts fail, are skipped, and traffic charges are incurred directly. Summary of the Invention

[0003] The purpose of this invention is to provide a method, device, and product for warning of remaining shared traffic packages, which solves the problem in the prior art that the remaining shared traffic packages that can be deducted at the same time in different resource pools of public cloud are not completely the same, resulting in the failure of traffic package remaining alarms, skipping alarms, and directly generating traffic charges.

[0004] To achieve the above objectives, embodiments of the present invention provide a method for providing early warning of remaining data allowance for shared data packets, comprising:

[0005] The first historical data of multiple first IPs using shared traffic resources within a first preset time period is used as input and input into a pre-obtained traffic analysis and prediction model to obtain the first predicted traffic consumption value of the first IP within a second preset time period after the current time.

[0006] Based on the first predicted traffic consumption value, traffic simulation deduction is performed on the current traffic of at least one shared traffic packet in the shared traffic resources to obtain the remaining traffic of the current traffic after the traffic simulation deduction.

[0007] If the remaining traffic is less than the first threshold, a traffic alarm will be issued.

[0008] Optionally, in the aforementioned remaining capacity warning method, when the shared traffic package is a first type of shared traffic package, the method further includes:

[0009] Obtain the remaining capacity ratio of the shared data package; wherein the remaining capacity ratio is the ratio of the current data volume of the shared data package to the total data volume of the shared data package;

[0010] If the margin ratio is less than the second threshold, the first historical data is input into the traffic analysis and prediction model.

[0011] Optionally, in the aforementioned margin warning method, when the at least one shared traffic packet is a designated IP shared traffic packet of a second IP, the method further includes:

[0012] The second IP address is identified as the first IP address.

[0013] Optionally, the aforementioned margin warning method further includes:

[0014] Acquire second historical data for a first time period and third historical data for a second time period from multiple first IPs to be trained; wherein the second time period is after the first time period;

[0015] Obtain the network topology map of the first IP based on the second historical data;

[0016] The network topology graph is input into a spatiotemporal graph convolutional network model with an attention mechanism to obtain prediction results; wherein, the prediction results are prediction data for the third historical data;

[0017] The spatiotemporal graph convolutional network model with the fusion attention mechanism is adjusted based on the prediction results and the third historical data to obtain the traffic analysis prediction model.

[0018] Optionally, in the aforementioned margin warning method, the step of obtaining the network topology map of the first IP based on the second historical data includes:

[0019] Abstract each of the first IP addresses into a network node, and obtain the set of network nodes;

[0020] Abstract the data transmission between the network nodes into edges, and obtain the edge set;

[0021] Obtain the adjacency matrix based on the network nodes and the edges;

[0022] The network topology graph is obtained based on the set of network nodes, the set of edges, and the adjacency matrix.

[0023] Optionally, in the aforementioned margin warning method, the spatiotemporal graph convolutional network model with integrated attention mechanism comprises a first fully connected layer, a first asynchronous spatiotemporal convolutional module, a first channel attention module, a second asynchronous spatiotemporal convolutional module, a second channel attention module, and a second fully connected layer connected in sequence; wherein the first asynchronous spatiotemporal convolutional module and the second asynchronous spatiotemporal convolutional module are each composed of multiple spatiotemporal convolutional layers including graph convolutional modules and spatiotemporal convolutional layers including asynchronous temporal convolutional modules, which are alternately stacked.

[0024] Optionally, in the aforementioned residual capacity early warning method, the step of issuing a traffic alarm includes:

[0025] Based on the first predicted traffic consumption value, simulate the traffic deduction process of the at least one shared traffic package within each third preset time period to obtain a traffic consumption diagram of the at least one shared traffic package; wherein, the second preset time period includes multiple third preset time periods;

[0026] The traffic consumption diagram will be sent to the customer as part of the traffic alarm notification.

[0027] Optionally, the remaining capacity warning method, wherein the step of performing simulated traffic deduction in the current traffic of at least one shared traffic packet in the shared traffic resources based on the first predicted traffic consumption value includes:

[0028] Obtain a list of currently valid shared traffic packets from the at least one shared traffic packet; wherein the shared traffic packets in the list are sorted from earliest to latest according to their expiration dates;

[0029] Each of the multiple first IPs is sequentially deducted from the current traffic in the order of the list, with off-peak traffic deducted first, and full-time traffic deducted after the off-peak traffic deduction is completed; wherein, the current traffic includes the off-peak traffic and the full-time traffic.

[0030] To achieve the above objectives, embodiments of the present invention also provide a shared data package remaining capacity warning device, comprising:

[0031] The first acquisition module is used to input the first historical data of multiple first IPs using shared traffic resources within a first preset time period as input to a pre-obtained traffic analysis and prediction model to obtain the first predicted traffic consumption value of the first IP within a second preset time period after the current time.

[0032] The second acquisition module is used to perform simulated traffic deduction on the current traffic of at least one shared traffic packet in the shared traffic resources according to the first predicted traffic consumption value, and to obtain the remaining traffic of the current traffic after the simulated traffic deduction.

[0033] The first processing module is used to issue a traffic alarm when the remaining traffic is less than a first threshold.

[0034] To achieve the above objectives, embodiments of the present invention also provide an electronic device, including: a processor, a memory, and a program or instructions stored in the memory and executable on the processor; wherein, when the processor executes the program or instructions, it implements the shared traffic packet remaining capacity warning method as described above.

[0035] To achieve the above objectives, embodiments of the present invention also provide a readable storage medium storing a program or instructions thereon, wherein the program or instructions, when executed by a processor, implement the steps in the shared traffic packet remaining capacity warning method as described above.

[0036] To achieve the above objectives, embodiments of the present invention also provide a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the shared traffic packet remaining capacity warning method as described above. The beneficial effects of the above technical solution of the present invention are as follows:

[0037] This invention, through its embodiment, inputs historical data of shared data packages into a traffic analysis and prediction model to obtain predicted traffic consumption values. It then simulates traffic deduction within the current traffic of all shared data packages until insufficient data is available for simulation. When this happens, a traffic alarm is triggered. By uniformly simulating the deduction of shared data packages from different resource pools and issuing an alarm when insufficient data is available, users are prompted to replenish shared data packages in advance. This avoids the problem of data package balance alarms becoming invalid, skipping alarms, and directly incurring traffic charges. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the shared traffic packet remaining capacity early warning method according to an embodiment of the present invention;

[0039] Figure 2 This is a schematic diagram illustrating the deduction of shared traffic packages in the shared traffic package remaining warning method according to an embodiment of the present invention;

[0040] Figure 3 This is a schematic diagram of the first type of shared traffic package deduction in the shared traffic package remaining warning method according to an embodiment of the present invention;

[0041] Figure 4 This is a schematic diagram illustrating the deduction of shared traffic packets for a specified IP address in the shared traffic packet balance warning method described in this embodiment of the invention.

[0042] Figure 5 This is a schematic diagram of the traffic analysis model of the shared traffic packet margin warning method according to an embodiment of the present invention;

[0043] Figure 6 This is a schematic diagram of the channel attention module in the shared traffic packet margin warning method according to an embodiment of the present invention;

[0044] Figure 7 This is a schematic diagram of the first type of shared traffic packet early warning method according to an embodiment of the present invention;

[0045] Figure 8 This is a schematic diagram illustrating the pre-warning of shared traffic packets for a specified IP address in the shared traffic packet remaining capacity pre-warning method described in this embodiment of the invention.

[0046] Figure 9 This is a schematic diagram of the shared traffic package remaining capacity warning device according to an embodiment of the present invention. Detailed Implementation

[0047] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0048] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the invention. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.

[0049] In various embodiments of the present invention, it should be understood that the sequence number of each process described below does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0050] In addition, the terms "system" and "network" are often used interchangeably in this article.

[0051] In the embodiments provided in this application, it should be understood that "B corresponding to Aβ" means that B is associated with Aβ, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0052] For ease of understanding, the following describes some aspects of the embodiments of the present invention:

[0053] like Figure 1 As shown in the figure, an embodiment of the present invention provides a method for predicting the remaining capacity of a shared data package, comprising:

[0054] S10, take the first historical data of multiple first IPs using shared traffic resources within a first preset time period as input, input it into the pre-obtained traffic analysis and prediction model, and obtain the first predicted traffic consumption value of the first IP within a second preset time period after the current time;

[0055] It should be noted that after obtaining the traffic analysis and prediction model in advance, the first preset duration, for example, seven days of the first historical data, is used to create a dataset based on the traffic data generated by each first IP in each hour. This dataset is then used as input. The first historical data is input into the traffic analysis and prediction model in batches for phased prediction. The prediction result is the first predicted traffic consumption value of the first IP in the second preset duration after the current time, which is usually the traffic usage of each first IP in the next natural day.

[0056] S20, based on the first predicted traffic consumption value, perform traffic simulation deduction on the current traffic of at least one shared traffic packet in the shared traffic resources to obtain the remaining traffic of the current traffic after the traffic simulation deduction;

[0057] It should be noted that, as Figure 2 As shown, when deducting traffic from shared traffic packages, the process is carried out sequentially in reverse chronological order of expiration time. After obtaining the first predicted traffic consumption value (usually the traffic usage of each first IP in the next natural day), the traffic deduction process is simulated every hour in the current traffic of at least one shared traffic package in the shared traffic resources (i.e., all traffic of the shared traffic packages currently arranged in reverse chronological order of expiration time) to obtain the remaining traffic.

[0058] S30, if the remaining traffic is less than the first threshold, issue a traffic alarm.

[0059] It should be noted that if the remaining traffic is less than the first threshold (usually 0), that is, if the current traffic is insufficient to cover the cost, the page will display a prominent color to remind the customer and issue a traffic alarm.

[0060] In this embodiment, historical data of shared data packages are input into a traffic analysis and prediction model to obtain predicted traffic consumption values. Traffic is simulated and deducted from the current traffic of all shared data packages until the current traffic is insufficient for the simulation and deduction. When the current traffic is insufficient for the simulation and deduction, a traffic alarm is triggered. By uniformly simulating and deducting shared data packages from different resource pools and triggering an alarm when the current traffic is insufficient, users can be prompted to replenish new shared data packages in advance. This avoids the problem of data package balance alarms becoming invalid, skipping alarms, and directly incurring traffic charges.

[0061] Optionally, in the aforementioned remaining capacity warning method, when the shared traffic package is a first type of shared traffic package, the method further includes:

[0062] Obtain the remaining capacity ratio of the shared data package; wherein the remaining capacity ratio is the ratio of the current data volume of the shared data package to the total data volume of the shared data package;

[0063] If the margin ratio is less than the second threshold, the first historical data is input into the traffic analysis and prediction model.

[0064] In this embodiment, the first type of shared traffic packet is a regular shared traffic packet that is not IP-limited, such as... Figure 3 As shown, the original traffic of IP A is deducted sequentially from the customer's currently valid shared traffic package resource list, and the deduction record is entered into the database until all ordinary shared traffic packages are deducted. The ordinary shared traffic package balance warning monitors and manages the customer's current ordinary shared traffic package balance. Without new subscriptions, the customer's ordinary shared traffic package balance will decrease over a month, and at the beginning of the next month, the total traffic package balance may increase due to the customer having designated active shared traffic packages. Traffic generated by an ordinary IP (i.e., the first IP) can only be offset by ordinary shared traffic packages. Therefore, the ordinary shared traffic package balance warning can provide balance reminders and alerts for all traffic packages consumed by IPs billed by traffic. Therefore, the following approach is adopted... Figure 7 As shown, the remaining effective ordinary shared traffic packets (remainA) and the total traffic value of the shared traffic packets (total) are calculated before deduction. After deduction, the remaining effective ordinary shared traffic packets (remainB) are calculated. If the ratio of the remaining packets after deduction is less than the second threshold (Alert Num), a simulated deduction is considered for the predicted traffic of the next natural day. Before this, if the ratio of the remaining packets is not less than the second threshold, the simulated deduction process is not required, thus avoiding waste of computing resources.

[0065] Optionally, in the aforementioned margin warning method, when the at least one shared traffic packet is a designated IP shared traffic packet of a second IP, the method further includes:

[0066] The second IP address is identified as the first IP address.

[0067] In this embodiment, such as Figure 4 As shown, when traffic packet TRAFFIC B is a shared traffic packet for designated IPs A and C, during the deduction process of IP B, TRAFFIC A and TRAFFIC C can be deducted normally, but the shared traffic packet for designated IPs is skipped. Traffic generated by IPs (i.e., the second IP) within the shared traffic packet subscribed by a designated IP can offset both designated and regular traffic packets. The designated IP deduction function is generally used for users with special business needs, where some IPs can offset part of the traffic packet resources, while other IPs do not use that traffic packet resource. For example... Figure 8As shown, IP A can offset TRAFFIC A and TRAFFIC C without IP limitation, and can also offset TRAFFIC B limited to IP A and IP C. Before the deduction, the remaining amount (IP AremainA) and total amount (IP Atotal) of valid ordinary shared traffic packets (for all shared traffic packets of the current IP) that can be offset by the current IP are calculated. After the deduction, the remaining amount (IPAremainB) of valid ordinary shared traffic packets that can be offset by the current IP are calculated. If the remaining capacity ratio (IP Aremain A / IP Total) before deduction is greater than the second threshold (Alert Num), and the remaining capacity ratio (IP Aremain B / IP Total) after deduction is less than the second threshold (Alert Num), then the second IP is used as the first IP, and its historical traffic is input into the traffic analysis and prediction model for prediction. If the prediction shows that the current traffic for the ordinary shared traffic package (including traffic packages with and without IP restrictions) for that IP is insufficient for simulated deduction within a future calendar day, then a remaining capacity warning for that IP is sent to the user. This avoids the situation where the unused remaining capacity of the shared traffic package is occupied due to the failure to set a specific IP for the traffic package, causing the remaining capacity of the shared traffic package to fail to reach the warning value and skip the alarm, thus directly incurring traffic charges.

[0068] Optionally, the aforementioned margin warning method further includes:

[0069] Acquire second historical data for a first time period and third historical data for a second time period from multiple first IPs to be trained; wherein the second time period is after the first time period;

[0070] Obtain the network topology map of the first IP based on the second historical data;

[0071] The network topology graph is input into a spatiotemporal graph convolutional network model with an attention mechanism to obtain prediction results; wherein, the prediction results are prediction data for the third historical data;

[0072] The spatiotemporal graph convolutional network model with the fusion attention mechanism is adjusted based on the prediction results and the third historical data to obtain the traffic analysis prediction model.

[0073] It should be noted that network traffic data has a temporal sequence, meaning that the traffic at the previous moment and the traffic at the current moment will affect the traffic at later moments. Deep learning models can be effectively applied to this type of scenario. In cloud-based networks, customer resources are all in the cloud. The process of network data from source to destination is actually a data flow process in the network structure. The traffic of different IPs has a certain spatial correlation due to data flow and affects each other.

[0074] In this embodiment, the network traffic flow of multiple first IPs is predicted by observing the network traffic data they have generated. The IPs held by the customer and their interactions are abstracted into a network topology graph G = (V, E, A), which is then input into a spatiotemporal graph convolutional network model with a fusion attention mechanism (CA-ASTGCN) for traffic analysis and prediction. After the model is built, a dataset is created based on the second historical data of multiple first IPs in the first time period, according to IP and hourly traffic data. The traffic data is then input into the spatiotemporal graph convolutional network model with a fusion attention mechanism in batches for phased prediction. The prediction results are compared with the third historical data in the second time period to adjust the spatiotemporal graph convolutional network model with a fusion attention mechanism, thereby obtaining the traffic analysis and prediction model.

[0075] Optionally, in the aforementioned margin warning method, the step of obtaining the network topology map of the first IP based on the second historical data includes:

[0076] Abstract each of the first IP addresses into a network node, and obtain the set of network nodes;

[0077] Abstract the data transmission between the network nodes into edges, and obtain the edge set;

[0078] Obtain the adjacency matrix based on the network nodes and the edges;

[0079] The network topology graph is obtained based on the set of network nodes, the set of edges, and the adjacency matrix.

[0080] In this embodiment, each first IP is abstracted as a network node V. Data forwarding between network nodes forms the edge E of the network topology graph. A is the adjacency matrix of the network topology graph. The network topology graph G = (V, E, A) is obtained, which reflects the connectivity between the nodes.

[0081] Optionally, in the aforementioned margin warning method, the spatiotemporal graph convolutional network model with fused attention mechanism includes a first fully connected layer, a first asynchronous spatiotemporal convolutional module, a first channel attention module, a second asynchronous spatiotemporal convolutional module, a second channel attention module, and a second fully connected layer connected in sequence; wherein, the first and second asynchronous spatiotemporal convolutional modules are each composed of multiple spatiotemporal convolutional layers including graph convolutional modules and spatiotemporal convolutional layers including asynchronous temporal convolutional modules, which are alternately stacked.

[0082] In this embodiment, the spatiotemporal graph convolutional network model that incorporates the attention mechanism is as follows: Figure 5 As shown, the model includes a first fully connected layer, a first asynchronous spatiotemporal convolutional module, a first channel attention module, a second asynchronous spatiotemporal convolutional module, a second channel attention module, and a second fully connected layer, connected sequentially. The two asynchronous spatiotemporal convolutional modules first extract node spatial information using the graph convolutional module, and then extract node temporal information using the asynchronous temporal convolutional module. The alternation of these two modules allows node information to be passed to its temporal and spatial neighbors. As the number of convolutional layers increases, the model retains a large amount of redundant information, leading to a decrease in model performance. To quickly obtain effective information, after multiple temporal convolutional modules, the first channel attention module and the second channel attention module are respectively used after the two asynchronous spatiotemporal convolutional modules to improve model performance. The first fully connected layer converts the input data features into high-dimensional spatial features, improving the network's representational ability. The output layer uses the second fully connected layer to convert the high-dimensional spatial data into prediction results.

[0083] The asynchronous spatiotemporal graph convolution operation (inputting the network topology graph into the asynchronous spatiotemporal convolution module) can be expressed as follows:

[0084]

[0085] in, This represents a weighted asynchronous spatiotemporal correlation matrix. Represents the weight matrix. This represents an asynchronous spatiotemporal correlation matrix, and ⊙ denotes element-wise multiplication. As inputs to the convolution operation, W and b are learnable parameters, h = σ(A) ′ XW+b) represents the graph convolution operation, and σ represents the activation function. Asynchronous spatiotemporal graph convolution operations aggregate a large amount of information from the previous time step (a time step is typically one hour, but can also be of other durations) and the next time step, and their structure is as follows: Figure 6As shown, the feature map after the asynchronous spatiotemporal convolution operation is first subjected to max pooling to obtain a feature vector of 1*C (number of channels). Then, it is fed into a two-layer neural network for training. The first layer reduces the number of parameters by using a small number of neurons, and the second layer has the same number of neurons as the input layer. The output feature vector is activated using a sigmoid (activation function), and the activated weight vector is weighted and summed with the input feature map.

[0086] Optionally, in the aforementioned margin warning method, step S30 includes:

[0087] Based on the first predicted traffic consumption value, simulate the traffic deduction process of the at least one shared traffic package within each third preset time period to obtain a traffic consumption diagram of the at least one shared traffic package; wherein, the second preset time period includes multiple third preset time periods;

[0088] The traffic consumption diagram will be sent to the customer as part of the traffic alarm notification.

[0089] In this embodiment, the shared data package deduction process for each hour is simulated based on the user's first predicted data consumption value for the next natural day. A data consumption diagram is drawn, indicating the remaining amount of shared data package before and after each deduction. This diagram is sent to the customer as the content of the data alarm. If the data package is insufficient for deduction, it is marked with a prominent color on the page to serve as a warning.

[0090] Optionally, in the aforementioned margin warning method, step S20 includes:

[0091] Obtain a list of currently valid shared traffic packets from the at least one shared traffic packet; wherein the shared traffic packets in the list are sorted from earliest to latest according to their expiration dates;

[0092] Each of the multiple first IPs is sequentially deducted from the current traffic in the order of the list, with off-peak traffic deducted first, and full-time traffic deducted after the off-peak traffic deduction is completed; wherein, the current traffic includes the off-peak traffic and the full-time traffic.

[0093] In this embodiment, the shared traffic package deduction order is as follows: deduct one IP at a time, prioritizing deduction during off-peak hours, and then deducting during full-time hours after the off-peak hours are deducted. Obtain the list of currently valid shared traffic packages and prioritize deducting the shared traffic package that expires first. If there is still a surplus after deducting the traffic packages in a single resource pool, then global shared traffic packages are deducted. The deduction logic is the same as the single resource pool deduction order. Global shared traffic packages can deduct traffic generated by IPs and IPv6 bandwidth that are billed by traffic in all resource pools of the customer.

[0094] like Figure 9As shown, in order to achieve the above objectives, embodiments of the present invention also provide a shared data package remaining capacity warning device, comprising:

[0095] The first acquisition module 901 is used to input the first historical data of multiple first IPs using shared traffic resources within a first preset time period as input into a pre-obtained traffic analysis and prediction model to obtain the first predicted traffic consumption value of the first IP within a second preset time period after the current time.

[0096] The second acquisition module 902 is used to perform traffic simulation deduction on the current traffic of at least one shared traffic packet in the shared traffic resources according to the first predicted traffic consumption value, and obtain the remaining traffic of the current traffic after the traffic simulation deduction.

[0097] The first processing module 903 is used to issue a traffic alarm when the remaining traffic is less than a first threshold.

[0098] Optionally, the remaining capacity warning device further includes:

[0099] The third acquisition module is used to acquire the remaining capacity ratio of the shared traffic package; wherein the remaining capacity ratio is the ratio of the current traffic of the shared traffic package to the total traffic value of the shared traffic package;

[0100] The second processing module is used to input the first historical data into the traffic analysis and prediction model when the margin ratio is less than the second threshold.

[0101] Optionally, the remaining capacity warning device further includes:

[0102] The first determining module is used to determine the second IP as the first IP.

[0103] Optionally, the remaining capacity warning device further includes:

[0104] The fourth acquisition module is used to acquire second historical data of the first time period and third historical data of the second time period of the first IP to be trained; wherein the second time period is after the first time period;

[0105] The fifth acquisition module is used to acquire the network topology map of the first IP based on the second historical data;

[0106] The sixth acquisition module is used to input the network topology graph into a spatiotemporal graph convolutional network model with an attention mechanism to obtain prediction results; wherein, the prediction results are prediction data for the third historical data;

[0107] The seventh acquisition module is used to adjust the spatiotemporal graph convolutional network model of the fusion attention mechanism according to the prediction results and the third historical data, and to acquire the traffic analysis prediction model.

[0108] Optionally, in the aforementioned residual capacity warning device, the fifth acquisition module includes:

[0109] The first acquisition unit is used to abstract each of the first IPs into a network node and acquire a set of network nodes;

[0110] The second acquisition unit is used to abstract the data transmission between the network nodes into edges and acquire an edge set.

[0111] The third acquisition unit is used to acquire the adjacency matrix based on the network nodes and the edges;

[0112] The fourth acquisition unit is used to acquire the network topology graph based on the network node set, edge set, and adjacency matrix.

[0113] Optionally, in the aforementioned margin warning device, the spatiotemporal graph convolutional network model with fused attention mechanism includes a first fully connected layer, a first asynchronous spatiotemporal convolutional module, a first channel attention module, a second asynchronous spatiotemporal convolutional module, a second channel attention module, and a second fully connected layer connected in sequence; wherein, the first asynchronous spatiotemporal convolutional module and the second asynchronous spatiotemporal convolutional module are each composed of multiple spatiotemporal convolutional layers including graph convolutional modules and spatiotemporal convolutional layers including asynchronous temporal convolutional modules, which are alternately stacked.

[0114] Optionally, in the aforementioned residual capacity warning device, the first processing module 903 includes:

[0115] The fifth acquisition unit is used to simulate the traffic deduction process of the at least one shared traffic package within each third preset time period based on the first predicted traffic consumption value, and to obtain a traffic consumption diagram of the at least one shared traffic package; wherein, the second preset time period includes multiple third preset time periods;

[0116] The first sending unit is used to send the traffic consumption diagram as the content of the traffic alarm prompt to the customer.

[0117] Optionally, in the aforementioned reserve warning method, the second acquisition module 902 includes:

[0118] The sixth acquisition unit is used to acquire a list of currently valid shared traffic packets in the at least one shared traffic packet; wherein the shared traffic packets in the list are sorted from earliest to latest according to their expiration dates;

[0119] The first processing unit is configured to perform simulated traffic deduction on each of the multiple first IPs in the current traffic according to the order of the list, first deducting the idle traffic, and then deducting the full-time traffic after the idle traffic deduction is completed; wherein, the current traffic includes the idle traffic and the full-time traffic.

[0120] It should be noted that the apparatus provided in this embodiment of the invention can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0121] To achieve the above objectives, embodiments of the present invention also provide an electronic device, including: a processor, a memory, and a program or instructions stored in the memory and executable on the processor; wherein, when the processor executes the program or instructions, it implements the shared traffic packet remaining capacity warning method as described above.

[0122] To achieve the above objectives, embodiments of the present invention also provide a readable storage medium storing a program or instructions thereon, wherein the program or instructions, when executed by a processor, implement the steps in the shared traffic packet remaining capacity warning method as described above.

[0123] It should be further noted that the terminals described in this specification include, but are not limited to, smartphones, tablets, etc., and many of the functional components described are referred to as modules in order to emphasize the independence of their implementation.

[0124] In this embodiment of the invention, the module can be implemented in software so that it can be executed by various types of processors. For example, an identified executable code module may include one or more physical or logical blocks of computer instructions, which may be constructed as objects, procedures, or functions. Nevertheless, the executable code of the identified module does not need to be physically located together, but may include different instructions stored in different bits, which, when logically combined, constitute the module and achieve the module's intended purpose.

[0125] In practice, an executable code module can be a single instruction or many instructions, and can even be distributed across multiple different code segments, different programs, and across multiple memory devices. Similarly, operational data can be identified within the module and can be implemented in any suitable form and organized within any suitable type of data structure. This operational data can be collected as a single dataset or distributed across different locations (including different storage devices), and can exist, at least in part, solely as electronic signals within the system or network.

[0126] When a module can be implemented using software, considering the current level of hardware technology, modules that can be implemented in software can be implemented using hardware circuits by those skilled in the art to achieve the corresponding functions, without considering cost. These hardware circuits include conventional very-large-scale integrated circuits (VLSI) or gate arrays, as well as existing semiconductors such as logic chips and transistors, or other discrete components. Modules can also be implemented using programmable hardware devices, such as field-programmable gate arrays, programmable array logic, and programmable logic devices.

[0127] To achieve the above objectives, embodiments of the present invention also provide a computer program product, which includes computer instructions that, when executed by a processor, implement the steps of the shared traffic packet remaining capacity warning method as described above.

[0128] The exemplary embodiments described above are with reference to the accompanying drawings. Many different forms and embodiments are feasible without departing from the spirit and teachings of the invention. Therefore, the invention should not be construed as limiting the exemplary embodiments set forth herein. Rather, these exemplary embodiments are provided to make the invention complete and convey the scope of the invention to those skilled in the art. In these drawings, component dimensions and relative dimensions may be exaggerated for clarity. The terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. As used herein, unless clearly indicated otherwise, the singular forms “a,” “an,” and “the” are intended to include all such forms. It will be further understood that the terms “comprising” and / or “including”, when used in this specification, indicate the presence of the stated features, integers, steps, operations, components, and / or elements, but do not exclude the presence or addition of one or more other features, integers, steps, operations, components, and / or groups thereof. Unless otherwise indicated, when stated, a range of values ​​includes the upper and lower limits of the range and any subranges in between.

[0129] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for early warning of remaining data allowance in shared data packages, characterized in that, include: The first historical data of multiple first IPs using shared traffic resources within a first preset time period is used as input and input into a pre-obtained traffic analysis and prediction model to obtain the first predicted traffic consumption value of the first IP within a second preset time period after the current time. Based on the first predicted traffic consumption value, traffic simulation deduction is performed on the current traffic of at least one shared traffic packet in the shared traffic resources to obtain the remaining traffic of the current traffic after the traffic simulation deduction. If the remaining traffic is less than the first threshold, a traffic alarm will be issued. Acquire second historical data for a first time period and third historical data for a second time period from multiple first IPs to be trained; wherein the second time period is after the first time period; Obtain the network topology map of the first IP based on the second historical data; The network topology graph is input into a spatiotemporal graph convolutional network model with an attention fusion mechanism to obtain prediction results; wherein, the prediction results are prediction data for the third historical data; the spatiotemporal graph convolutional network model with an attention fusion mechanism includes a first fully connected layer, a first asynchronous spatiotemporal convolutional module, a first channel attention module, a second asynchronous spatiotemporal convolutional module, a second channel attention module, and a second fully connected layer connected in sequence; the first asynchronous spatiotemporal convolutional module and the second asynchronous spatiotemporal convolutional module are each composed of multiple spatiotemporal convolutional layers including graph convolutional modules and spatiotemporal convolutional layers including asynchronous temporal convolutional modules, which are alternately stacked; The spatiotemporal graph convolutional network model of the fusion attention mechanism is adjusted based on the prediction results and the third historical data to obtain the traffic analysis prediction model; The step of obtaining the network topology map of the first IP based on the second historical data includes: Abstract each of the first IP addresses into a network node, and obtain the set of network nodes; Abstract the data transmission between the network nodes into edges, and obtain the edge set; Obtain the adjacency matrix based on the network nodes and the edges; The network topology graph is obtained based on the set of network nodes, the set of edges, and the adjacency matrix.

2. The margin early warning method according to claim 1, characterized in that, When the shared traffic package is a first type of shared traffic package, the method further includes: Obtain the remaining capacity ratio of the shared data package; wherein the remaining capacity ratio is the ratio of the current data volume of the shared data package to the total data volume of the shared data package; If the margin ratio is less than the second threshold, the first historical data is input into the traffic analysis and prediction model.

3. The margin early warning method according to claim 1, characterized in that, When the at least one shared traffic packet is a designated IP shared traffic packet of a second IP, the method further includes: The second IP address is identified as the first IP address.

4. The margin early warning method according to claim 1, characterized in that, The traffic alert notification includes: Based on the first predicted traffic consumption value, simulate the traffic deduction process of the at least one shared traffic package within each third preset time period to obtain a traffic consumption diagram of the at least one shared traffic package; wherein, the second preset time period includes multiple third preset time periods; The traffic consumption diagram will be sent to the customer as part of the traffic alarm message.

5. The margin early warning method according to claim 1, characterized in that, The step of performing simulated traffic deduction based on the first predicted traffic consumption value in the current traffic of at least one shared traffic packet in the shared traffic resources includes: Obtain a list of currently valid shared traffic packets from the at least one shared traffic packet; wherein the shared traffic packets in the list are sorted from earliest to latest according to their expiration dates; Each of the multiple first IPs is sequentially deducted from the current traffic in the order of the list, with off-peak traffic deducted first, and full-time traffic deducted after the off-peak traffic deduction is completed; wherein, the current traffic includes the off-peak traffic and the full-time traffic.

6. A shared data package remaining capacity early warning device, characterized in that, include: The first acquisition module is used to input the first historical data of multiple first IPs using shared traffic resources within a first preset time period as input to a pre-obtained traffic analysis and prediction model to obtain the first predicted traffic consumption value of the first IP within a second preset time period after the current time. The second acquisition module is used to perform simulated traffic deduction on the current traffic of at least one shared traffic packet in the shared traffic resources according to the first predicted traffic consumption value, and to obtain the remaining traffic of the current traffic after the simulated traffic deduction. The first processing module is used to issue a traffic alarm when the remaining traffic is less than a first threshold. The fourth acquisition module is used to acquire second historical data of the first time period and third historical data of the second time period of the first IP to be trained; wherein the second time period is after the first time period; The fifth acquisition module is used to acquire the network topology map of the first IP based on the second historical data; The sixth acquisition module is used to input the network topology graph into a spatiotemporal graph convolutional network model with an attention fusion mechanism to obtain prediction results; wherein, the prediction results are prediction data for the third historical data; the spatiotemporal graph convolutional network model with an attention fusion mechanism includes a first fully connected layer, a first asynchronous spatiotemporal convolutional module, a first channel attention module, a second asynchronous spatiotemporal convolutional module, a second channel attention module, and a second fully connected layer connected in sequence; the first asynchronous spatiotemporal convolutional module and the second asynchronous spatiotemporal convolutional module are each composed of multiple spatiotemporal convolutional layers including graph convolutional modules and spatiotemporal convolutional layers including asynchronous temporal convolutional modules, which are alternately stacked; The seventh acquisition module is used to adjust the spatiotemporal graph convolutional network model of the fusion attention mechanism according to the prediction results and the third historical data, and acquire the traffic analysis prediction model. The fifth acquisition module includes: The first acquisition unit is used to abstract each of the first IPs into a network node and acquire a set of network nodes; The second acquisition unit is used to abstract the data transmission between the network nodes into edges and acquire an edge set. The third acquisition unit is used to acquire the adjacency matrix based on the network nodes and the edges; The fourth acquisition unit is used to acquire the network topology graph based on the network node set, edge set, and adjacency matrix.

7. An electronic device, comprising: A processor, a memory, and a program or instructions stored in the memory and executable on the processor; characterized in that, when the processor executes the program or instructions, it implements the shared traffic packet remaining capacity warning method as described in any one of claims 1-5.

8. A readable storage medium having a program or instructions stored thereon, characterized in that, When the program or instructions are executed by the processor, they implement the steps in the shared traffic packet margin warning method as described in any one of claims 1-5.

9. A computer program product, characterized in that, It includes computer instructions, which, when executed by a processor, implement the steps of the shared traffic packet remaining capacity warning method as described in any one of claims 1-5.

Images