A method and system for generating a virtual traffic card

Abstract

The present invention discloses a method and system for generating a virtual traffic card, which comprehensively considers the balance between request frequency, system computing power load and operator operating income, reduces the computing power pressure of the system, and can also ensure the operating income of the operator, and also meet the traffic needs of users. On the other hand, based on the virtual traffic card to generate request information and historical request data to generate traffic card information, the traffic card information generated after analyzing the user's personal situation can better meet the specific needs of the user and avoid waste of resources. If it cannot be balanced, a virtual traffic card that can be balanced and close to the user's needs is generated for the user to choose.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method and system for generating a virtual traffic card. Background Art

[0002] Virtual-Embedded-Subscriber Identity Module (vSIM) is a way of communication without a physical SIM card, relying entirely on the software and hardware of the communication module itself. The communication module with vSIM function, in conjunction with the underlying software specially customized for vSIM, implements built-in encrypted storage of data, such as International Mobile Equipment Identity (IMEI), authentication key (KI), etc. When logging on to the network, authenticating, and communicating, the corresponding logic is automatically processed, so as to provide a stable communication experience without the need for a physical SIM card. The Global SIM Connection Cloud Service provides vSIM-type connection services. Customers' devices do not need physical cards. They can directly connect to the Internet using communication modules with built-in vSIM technology software. It has more flexible functions than physical cards and supports the selection of global mobile network traffic provided by the Global SIM Connection Service. The Global SIM Connection Service configures the code number resources based on the IMEI and connection service package of the module provided by the customer. When the customer's device using the module is powered on and started, the corresponding code number is automatically downloaded from the Global SIM Connection Service and the networking function is enabled. After the user activates the vSIM card, he / she can configure and bind the vSIM card to the virtual communication service provided by the operator (such as a virtual traffic card) to connect to the Internet.

[0003] In virtual communication technology, virtual traffic is an important communication method for network communication. Currently, communication operators provide traffic packages (traffic cards) of different types and specifications (different data volumes) for users to choose from. However, traffic packages in this way are generated in batches and cannot meet user needs: users can only choose batch-generated traffic packages (traffic cards) provided by operators, and cannot choose traffic cards with corresponding data volumes according to specific network traffic needs. Users have a poor experience using traffic cards. If corresponding traffic cards are generated for users as long as the user requests, it will also bring great consumption of computing resources, and it is also not conducive to the operation of network operators.

[0004] Therefore, a method for generating a virtual traffic card that can meet the traffic demands of users, save computing resources, and ensure the operating benefits of network operators is needed. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for generating a virtual traffic card to solve the above-mentioned problems existing in the prior art.

[0006] An embodiment of the present invention provides a method for generating a virtual traffic card, the method comprising:

[0007] If a request information is received from a user's virtual traffic card, if there is historical request data of the user, the historical request data of the user is obtained; the historical request data includes the historical request time and the historical request traffic;

[0008] Obtain the operator's current revenue price based on the virtual traffic card generation request information;

[0009] Generate request information based on virtual traffic cards to predict system computing power consumption;

[0010] Get historical request frequency based on historical request time;

[0011] Determine whether the historical request frequency, system computing power consumption and current revenue price meet the balance conditions;

[0012] If the historical request frequency, system computing power consumption and current revenue price meet the balance condition, the traffic card information is generated based on the virtual traffic card generation request information and historical request data;

[0013] Send the traffic card information to the user.

[0014] Optionally, the method further includes:

[0015] If the traffic card confirmation information sent by the user is received, a virtual traffic card is generated, and the traffic information of the virtual traffic card is the traffic card information.

[0016] Optionally, generating flow card information based on the virtual flow card generation request information and historical request data includes:

[0017] Arrange the virtual traffic card generation request information and historical request data into a traffic request sequence in the order of request time;

[0018] Extract features of the traffic request sequence using a mixed Gaussian model to obtain a first feature vector;

[0019] Extract features of the traffic request sequence through Fourier transform to obtain a second feature vector;

[0020] The first eigenvector and the second eigenvector are merged to obtain a third eigenvector;

[0021] Generate traffic card information based on the third eigenvector.

[0022] Optionally, the first eigenvector and the second eigenvector are fused to obtain a third eigenvector, including:

[0023] The first eigenvector and the second eigenvector are input into the first convolutional neural network and the second convolutional neural network respectively. The first convolutional neural network and the second convolutional neural network process the first eigenvector and the second eigenvector respectively, and perform feature fusion operation through the fusion network to output the third eigenvector, which is specifically:

[0024] A fusion network is obtained, which includes multiple network layers; wherein the fusion weight of the i-th layer of the fusion network is wi, wi=(w1i+w2i) / 2, w1i is the weight matrix of the i-th layer of the first convolutional neural network, and w2i is the weight matrix of the i-th layer of the second convolutional neural network; a union Ui of the input IN1i of the i-th layer of the first convolutional neural network and the input IN2i of the i-th layer of the second convolutional neural network is obtained; a merge matrix Mi of the i-th layer is obtained, and the elements of the main diagonal of the merge matrix Mi of the i-th layer are the elements of the union Ui;

[0025] Based on the fusion weight wi, the output OUT1i of the i-th layer of the first convolutional neural network and the output OUT2i of the i-th layer of the second convolutional neural network are fused to obtain the fusion feature Vi of the i-th layer;

[0026] Use the merged matrix Mi of the i-th layer as the convolution kernel to perform a convolution operation on the fusion feature Vi of the i-th layer to obtain the convolution feature coni of the i-th layer;

[0027] Obtain the weighted feature Ri of the i-th layer of the third convolutional neural network; the weighted feature Ri is equal to the weighted sum of the convolution feature coni of the i-th layer and the output of the i-1-th layer of the third convolutional neural network; when i=1, the input of the i-1-th layer of the third convolutional neural network is 0;

[0028] The fusion is performed in the above manner until the last layer, and the output of the last layer of the third convolutional neural network is used as the third feature vector;

[0029] Here, the value of i is a positive integer.

[0030] Optionally, determine whether the historical request frequency, system computing power consumption, and current revenue price meet the balance conditions, including:

[0031] If the historical request frequency is greater than the set value, and the system computing power consumption and the current revenue price satisfy the following formula (1), it is determined that the historical request frequency, system computing power consumption and the current revenue price meet the balance condition:

[0032] a*c

[0033] ​Where c is the system computing power consumption, a is the proportional coefficient, and Q is the current profit price; the proportional coefficient a is determined by the current system computing power C, the computing power consumption price coefficient q and the system computing power consumption. Specifically, the proportional coefficient a is obtained by the following formula (2):

[0034] a=q*c / C (2);

[0035] If the historical request frequency is less than or equal to the set value, and the system computing power consumption and the current revenue price do not satisfy formula (1), it is determined that the historical request frequency, the system computing power consumption and the current revenue price do not meet the balance condition.

[0036] The embodiment of the present invention further provides a system for generating a virtual traffic card, the system comprising:

[0037] An acquisition module is used to, upon receiving a request information generated by a user's virtual traffic card, acquire the user's historical request data if there is any; the historical request data includes the historical request time and the historical request traffic;

[0038] A prediction module is used to obtain the operator's current revenue price based on the request information generated by the virtual traffic card; predict the system computing power consumption based on the request information generated by the virtual traffic card; and obtain the historical request frequency based on the historical request time;

[0039] The traffic card information generation module is used to determine whether the historical request frequency, system computing power consumption and current revenue price meet the balance conditions; if the historical request frequency, system computing power consumption and current revenue price meet the balance conditions, the traffic card information is generated based on the virtual traffic card request information and historical request data; and the traffic card information is sent to the user.

[0040] Optionally, the system further includes:

[0041] The flow card generation module is used to generate a virtual flow card if flow card confirmation information sent by the user is received, and the flow information of the virtual flow card is the flow card information.

[0042] Compared with the prior art, the embodiments of the present invention achieve the following beneficial effects:

[0043] The embodiment of the present invention provides a method and system for generating a virtual traffic card, which comprehensively considers the balance between request frequency, system computing power load and operator operating income, reduces the computing power pressure of the system, and at the same time ensures the operator's operating income and meets the user's traffic needs. On the other hand, based on the virtual traffic card to generate request information and historical request data to generate traffic card information, the traffic card information generated after analysis in combination with the user's personal situation can better meet the user's specific needs and avoid waste of resources. If the balance cannot be achieved, a virtual traffic card that can be balanced and close to the user's needs is generated for the user to choose. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 The present invention provides a flowchart of a method for generating a virtual traffic card.

[0045] Figure 2 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0046] Markings in the figure: 500 - bus; 501 - receiver; 502 - processor; 503 - transmitter; 504 - memory; 505 - bus interface. DETAILED DESCRIPTION

[0047] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0048] Example

[0049] The embodiment of the present invention provides a method for generating a virtual traffic card. Figure 1 , the method comprising:

[0050] S101: If a request message for generating a virtual traffic card of a user is received, and if there is historical request data of the user, the historical request data of the user is obtained.

[0051] The virtual traffic card generation request information includes the request time and the requested data volume, and the historical request data includes the historical request time and the historical request traffic volume. In an embodiment of the present invention, the system monitors in real time whether the user's virtual traffic card generation request information is received. If the user's virtual traffic card generation request information is received, the step S101 is executed. After receiving the user's virtual traffic card generation request information, the historical request data of the user who sent the virtual traffic card generation request information is obtained. If the user's historical request data does not exist in the system, the traffic card information is generated according to the virtual traffic card generation request information. At this time, the data volume in the traffic card information is the requested data volume.

[0052] S102: Obtain the current revenue price of the operator based on the virtual traffic card generation request information. In the embodiment of the present invention, the current revenue price is equal to the requested data volume in the virtual traffic card generation request information multiplied by the data unit price, which is determined by the operator. Generally, the data unit price is 0.1-0.5, and the unit is yuan / G, where G is the data volume unit of the traffic.

[0053] S103: Predicting system computing power consumption based on the virtual traffic card generation request information. Specifically, the system computing power consumption is equal to the amount of request data in the virtual traffic card generation request information multiplied by the unit consumption of the generation card computing power consumption.

[0054] In the system, the system's computing power consumption rules are pre-set, that is, how much computing power is needed to generate a virtual traffic card containing a set amount of data, and how much computing power consumption will bring about how much profit price. For example, generating a virtual traffic card with a data volume of 1G requires 5TOPS. TOPS stands for Tera Operations Per Second, which is a unit of processor computing power. Consuming 1TOPS of computing power to generate a virtual traffic card will bring the operator a profit price of 0.1 yuan. Optionally, the value of the unit consumption of the computing power consumption of the generated card is 1-10, and optionally, the unit consumption of the computing power consumption of the generated card = 5.

[0055] S104: Obtaining the historical request frequency based on the historical request time: Historical request frequency = number of historical requests / historical request duration, where the historical request duration is equal to the time interval between the earliest historical request time and the latest historical request time.

[0056] S105: Determine whether the historical request frequency, system computing power consumption and current revenue price meet the balance condition.

[0057] In the embodiment of the present invention, it is determined whether the historical request frequency, the system computing power consumption and the current revenue price meet the balance condition, which can be:

[0058] If the historical request frequency is greater than the set value, and the average value of the historical request traffic is greater than the threshold, and the current revenue price is less than the predetermined value, it is determined that the historical request frequency, system computing power consumption, and current revenue price meet the balance condition.

[0059] The set value can be 0.2-0.5 times / day, the threshold can be 50G-100G, and the profit price can be 5 yuan, 10 yuan, or 100 yuan.

[0060] Optionally, S105 can also be:

[0061] If the historical request frequency is greater than the set value, and the system computing power consumption and the current revenue price satisfy the following formula (1), it is determined that the historical request frequency, system computing power consumption and the current revenue price meet the balance condition:

[0062] a*c

[0063] Where c is the system computing power consumption, a is the proportional coefficient, and Q is the current profit price; the proportional coefficient a is determined by the current system computing power C, the computing power consumption price coefficient q and the system computing power consumption. Specifically, the proportional coefficient a is obtained by the following formula (2):

[0064] a=q*c / C (2)

[0065] If the historical request frequency is less than or equal to the set value, and the system computing power consumption and the current revenue price do not satisfy formula (1), it is determined that the historical request frequency, the system computing power consumption and the current revenue price do not meet the balance condition.

[0066] By adopting the above solution, a balance is ensured between the system's user needs, computing resources, and the operator's cloud operating benefits.

[0067] S106: If the historical request frequency, system computing power consumption and current revenue price meet the balance condition, the traffic card information is generated based on the virtual traffic card generation request information and the historical request data.

[0068] S107: Send the traffic card information to the user.

[0069] By adopting the above solution, on the one hand, the balance between request frequency, system computing power load and operator operating income is comprehensively considered, which reduces the computing power pressure of the system, ensures the operating income of the operator, and meets the traffic needs of users. On the other hand, based on the virtual traffic card to generate request information and historical request data to generate traffic card information, the traffic card information generated after analyzing the user's personal situation can better meet the specific needs of users and avoid waste of resources. If it cannot be balanced, a virtual traffic card that can be balanced and close to the user's needs is generated for the user to choose.

[0070] As an optional implementation, the method for generating the virtual traffic card further includes:

[0071] If the historical request frequency is greater than the set value, and the average value of the historical request traffic is less than or equal to the threshold, the traffic card information is generated based on the virtual traffic card request information and the historical request data, and the traffic card information is sent to the user.

[0072] If the historical request frequency is less than the set value, the flow card information is generated based on the virtual flow card generation request information, and the flow card information is sent to the user. ​

[0073] After sending the flow card information, the method for generating the virtual flow card further includes: if flow card confirmation information sent by the user is received, generating a virtual flow card, and the flow information of the virtual flow card is the flow card information.

[0074] In an embodiment of the present invention, generating flow card information based on virtual flow card generation request information and historical request data includes:

[0075] Arrange the virtual traffic card generation request information and historical request data into a traffic request sequence in the order of request time. Extract features of the traffic request sequence through a mixed Gaussian model to obtain a first feature vector. Extract features of the traffic request sequence through Fourier transform to obtain a second feature vector. Fuse the first feature vector and the second feature vector to obtain a third feature vector. Generate traffic card information based on the third feature vector.

[0076] The first eigenvector and the second eigenvector are fused to obtain a third eigenvector, including:

[0077] The first eigenvector and the second eigenvector are input into the first convolutional neural network and the second convolutional neural network respectively. The first convolutional neural network and the second convolutional neural network process the first eigenvector and the second eigenvector respectively, and perform feature fusion operation through the fusion network to output the third eigenvector, which is specifically:

[0078] A fusion network is obtained, which includes multiple network layers; wherein the fusion weight of the i-th layer of the fusion network is wi, wi=(w1i+w2i) / 2, w1i is the weight matrix of the i-th layer of the first convolutional neural network, and w2i is the weight matrix of the i-th layer of the second convolutional neural network. A union Ui of the input IN1i of the i-th layer of the first convolutional neural network and the input IN2i of the i-th layer of the second convolutional neural network is obtained. A merge matrix Mi of the i-th layer is obtained, and the elements of the main diagonal of the merge matrix Mi of the i-th layer are the elements of the union Ui; the off-diagonal elements of the merge matrix Mi of the i-th layer are 0.

[0079] In the embodiment of the present invention, when i=1, the input IN1i of the i-th layer of the first convolutional neural network is the first eigenvector, and the input IN2i of the i-th layer of the second convolutional neural network is the second eigenvector. The output of the i-th layer of the first convolutional neural network is the input of the i+1-th layer of the first convolutional neural network, and the output of the i-th layer of the second convolutional neural network is the input of the i+1-th layer of the second convolutional neural network. The value of i is a positive integer. In the embodiment of the present invention, the number of network layers is 5, that is, the fusion network includes 5 network layers, the first convolutional neural network and the 5-layer network, the second convolutional neural network and the 5-layer network, i=1, 2, 3, 4, 5.

[0080] Based on the fusion weight wi, the output OUT1i of the i-th layer of the first convolutional neural network and the output OUT2i of the i-th layer of the second convolutional neural network are fused to obtain the fusion feature Vi of the i-th layer. Specifically, Vi is obtained by weighted fusion of OUT1i and OUT2i, that is, Vi=(1-w)OUT1i+wOUT2i, where w is the weighting factor. Optionally, w can be the feature value with the above fusion weight wi. Optionally, w=0.5.

[0081] The fusion feature Vi of the i-th layer is convolved with the merged matrix Mi of the i-th layer as the convolution kernel to obtain the convolution feature coni of the i-th layer.

[0082] Obtaining the weighted feature Ri of the i-th layer of the third convolutional neural network; the weighted feature Ri is equal to the weighted sum of the convolution feature coni of the i-th layer and the output of the i-1-th layer of the third convolutional neural network; when i=1, the input of the i-1-th layer of the third convolutional neural network is 0. In an embodiment of the present invention, the first convolutional neural network, the second convolutional neural network, and the third convolutional neural network have the same number of network layers.

[0083] The fusion is performed in the above manner until the last layer, and the output of the last layer of the third convolutional neural network is used as the third eigenvector.

[0084] By adopting the above scheme to fuse and obtain the third eigenvector, the first eigenvector and the second eigenvector are deeply integrated, and the correlation between the first eigenvector and the second eigenvector is also mined, so that the third eigenvector can accurately characterize the user's traffic demand.

[0085] Generate the flow card information based on the third eigenvector. Specifically, obtain the flow information corresponding to the third eigenvector from the database as the flow card information. That is, the flow information corresponding to the third eigenvector is pre-stored in the database.

[0086] As an optional implementation manner, optionally, after S106, the method for generating the virtual traffic card further includes:

[0087] If the historical request frequency, system computing power consumption and current revenue price do not meet the balance condition, the traffic card information is generated based on the system computing power consumption, current revenue price, virtual traffic card generation request information and historical request data. Specifically:

[0088] The initial flow card information is obtained by the above-mentioned method of generating flow card information based on the virtual flow card request information and the historical request data.

[0089] Obtain the traffic information contained in the initial traffic card information, and obtain the first computing power and the first price corresponding to the traffic information through the methods shown in S102 and S103 above;

[0090] The cross entropy between the first computing power and the system computing power consumption is obtained, which is recorded as the first cross entropy. The cross entropy between the first price and the current profit price is obtained, which is recorded as the second cross entropy. The first cross entropy is used as c in the above formula (1), and the second cross entropy is used as Q in the above formula (1). At this time, if formula (1) is satisfied, the traffic in the traffic card information is determined to be = initial traffic card information + c*Q initial traffic card information.

[0091] Based on the above-mentioned method for generating a virtual traffic card, an embodiment of the present invention provides a system for generating a virtual traffic card for executing the above-mentioned method, the system comprising:

[0092] An acquisition module is used to, upon receiving a request information generated by a user's virtual traffic card, acquire the user's historical request data if there is any; the historical request data includes the historical request time and the historical request traffic;

[0093] A prediction module is used to obtain the operator's current revenue price based on the request information generated by the virtual traffic card; predict the system computing power consumption based on the request information generated by the virtual traffic card; and obtain the historical request frequency based on the historical request time;

[0094] The traffic card information generation module is used to determine whether the historical request frequency, system computing power consumption and current revenue price meet the balance conditions; if the historical request frequency, system computing power consumption and current revenue price meet the balance conditions, the traffic card information is generated based on the virtual traffic card request information and historical request data; and the traffic card information is sent to the user.

[0095] Optionally, the system further includes:

[0096] The flow card generation module is used to generate a virtual flow card if flow card confirmation information sent by the user is received, and the flow information of the virtual flow card is the flow card information.

[0097] The specific implementation methods of the functions of each module of the above system are as described in the above method for generating a virtual traffic card, and will not be repeated here.

[0098] The embodiment of the present invention also provides an electronic device for integrating the above-mentioned virtual traffic card generation system, such as Figure 2 As shown, the electronic device includes a memory 504, a processor 502, and a computer program stored in the memory 504 and executable on the processor 502. When the processor 502 executes the program, the steps of any method of generating a virtual traffic card described above are implemented.

[0099] Among them, Figure 2 In the embodiment of the present invention, a bus architecture (represented by bus 500) is shown, which may include any number of interconnected buses and bridges, and bus 500 links various circuits including one or more processors represented by processor 502 and memory represented by memory 504. Bus 500 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 505 provides an interface between bus 500 and receiver 501 and transmitter 503. Receiver 501 and transmitter 503 may be the same element, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 502 is responsible for managing bus 500 and general processing, while memory 504 may be used to store data used by processor 502 when performing operations.

[0100] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of any method of generating a virtual traffic card described above are implemented.

[0101] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0102] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0103] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0104] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0105] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0106] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the apparatus according to an embodiment of the present invention. The present invention may also be implemented as a device or device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention may be stored on a computer-readable medium, or may have the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

Claims

1. A method for generating a virtual traffic card, characterized in that: The method comprises: If a request information is received from a user's virtual traffic card, if there is historical request data of the user, the historical request data of the user is obtained; the historical request data includes the historical request time and the historical request traffic; Obtain the operator's current revenue price based on the virtual traffic card generation request information; Generate request information based on virtual traffic cards to predict system computing power consumption; Get historical request frequency based on historical request time; Determine whether the historical request frequency, system computing power consumption and current revenue price meet the balance conditions; If the historical request frequency, system computing power consumption and current revenue price meet the balance condition, the traffic card information is generated based on the virtual traffic card generation request information and historical request data; Send the traffic card information to the user; Generate traffic card information based on virtual traffic card generation request information and historical request data, including: Arrange the virtual traffic card generation request information and historical request data into a traffic request sequence in the order of request time; Extract features of the traffic request sequence using a mixed Gaussian model to obtain a first feature vector; Extract features of the traffic request sequence through Fourier transform to obtain a second feature vector; The first eigenvector and the second eigenvector are merged to obtain a third eigenvector; Generate flow card information based on the third eigenvector; The first eigenvector and the second eigenvector are fused to obtain a third eigenvector, including: The first eigenvector and the second eigenvector are input into the first convolutional neural network and the second convolutional neural network respectively. The first convolutional neural network and the second convolutional neural network process the first eigenvector and the second eigenvector respectively, and perform feature fusion operation through the fusion network to output the third eigenvector, which is specifically: A fusion network is obtained, which includes multiple network layers; wherein the fusion weight of the i-th layer of the fusion network is wi, wi=(w1i+w2i) / 2, w1i is the weight matrix of the i-th layer of the first convolutional neural network, and w2i is the weight matrix of the i-th layer of the second convolutional neural network; a union Ui of the input IN1i of the i-th layer of the first convolutional neural network and the input IN2i of the i-th layer of the second convolutional neural network is obtained; a merge matrix Mi of the i-th layer is obtained, and the elements of the main diagonal of the merge matrix Mi of the i-th layer are the elements of the union Ui; Based on the fusion weight wi, the output OUT1i of the i-th layer of the first convolutional neural network and the output OUT2i of the i-th layer of the second convolutional neural network are fused to obtain the fusion feature Vi of the i-th layer; Use the merged matrix Mi of the i-th layer as the convolution kernel to perform a convolution operation on the fusion feature Vi of the i-th layer to obtain the convolution feature coni of the i-th layer; Obtain the weighted feature Ri of the i-th layer of the third convolutional neural network; the weighted feature Ri is equal to the weighted sum of the convolution feature coni of the i-th layer and the output of the i-1-th layer of the third convolutional neural network; when i=1, the input of the i-1-th layer of the third convolutional neural network is 0; The fusion is performed in the above manner until the last layer, and the output of the last layer of the third convolutional neural network is used as the third feature vector; Among them, the value of i is a positive integer; Determine whether the historical request frequency, system computing power consumption, and current revenue price meet the balance conditions, including: If the historical request frequency is greater than the set value, and the system computing power consumption and the current revenue price satisfy the following formula (1), it is determined that the historical request frequency, system computing power consumption and the current revenue price meet the balance condition: a*c, where c is the system computing power consumption, a is the proportional coefficient, and Q is the current profit price; the proportional coefficient a is determined by the current system computing power C, the computing power consumption price coefficient q and the system computing power consumption. Specifically, the proportional coefficient a is obtained by the following formula (2): a=q*c / C (2); If the historical request frequency is less than or equal to the set value, and the system computing power consumption and the current revenue price do not satisfy formula (1), it is determined that the historical request frequency, the system computing power consumption and the current revenue price do not meet the balance condition. The method further comprises:

2. The method for generating a virtual traffic card according to claim 1, characterized in that: If the traffic card confirmation information sent by the user is received, a virtual traffic card is generated, and the traffic information of the virtual traffic card is the traffic card information. The system comprises:

3. A system for generating a virtual traffic card, characterized in that: An acquisition module is used to, upon receiving a request information generated by a user's virtual traffic card, acquire the user's historical request data if there is any; the historical request data includes the historical request time and the historical request traffic; A prediction module is used to obtain the operator's current revenue price based on the request information generated by the virtual traffic card; predict the system computing power consumption based on the request information generated by the virtual traffic card; and obtain the historical request frequency based on the historical request time; The flow card information generation module is used to determine whether the historical request frequency, system computing power consumption and current revenue price meet the balance condition; if the historical request frequency, system computing power consumption and current revenue price meet the balance condition, the flow card information is generated based on the virtual flow card generation request information and historical request data; and the flow card information is sent to the user; Generate traffic card information based on virtual traffic card generation request information and historical request data, including: Arrange the virtual traffic card generation request information and historical request data into a traffic request sequence in the order of request time; Extract features of the traffic request sequence using a mixed Gaussian model to obtain a first feature vector; Extract features of the traffic request sequence through Fourier transform to obtain a second feature vector; The first eigenvector and the second eigenvector are merged to obtain a third eigenvector; Generate flow card information based on the third eigenvector; The first eigenvector and the second eigenvector are fused to obtain a third eigenvector, including: The first eigenvector and the second eigenvector are input into the first convolutional neural network and the second convolutional neural network respectively. The first convolutional neural network and the second convolutional neural network process the first eigenvector and the second eigenvector respectively, and perform feature fusion operation through the fusion network to output the third eigenvector, which is specifically: ​ A fusion network is obtained, which includes multiple network layers; wherein the fusion weight of the i-th layer of the fusion network is wi, wi=(w1i+w2i) / 2, w1i is the weight matrix of the i-th layer of the first convolutional neural network, and w2i is the weight matrix of the i-th layer of the second convolutional neural network; a union Ui of the input IN1i of the i-th layer of the first convolutional neural network and the input IN2i of the i-th layer of the second convolutional neural network is obtained; a merge matrix Mi of the i-th layer is obtained, and the elements of the main diagonal of the merge matrix Mi of the i-th layer are the elements of the union Ui; Based on the fusion weight wi, the output OUT1i of the i-th layer of the first convolutional neural network and the output OUT2i of the i-th layer of the second convolutional neural network are fused to obtain the fusion feature Vi of the i-th layer; Use the merged matrix Mi of the i-th layer as the convolution kernel to perform a convolution operation on the fusion feature Vi of the i-th layer to obtain the convolution feature coni of the i-th layer; Obtain the weighted feature Ri of the i-th layer of the third convolutional neural network; the weighted feature Ri is equal to the weighted sum of the convolution feature coni of the i-th layer and the output of the i-1-th layer of the third convolutional neural network; when i=1, the input of the i-1-th layer of the third convolutional neural network is 0; The fusion is performed in the above manner until the last layer, and the output of the last layer of the third convolutional neural network is used as the third feature vector; Among them, the value of i is a positive integer; Determine whether the historical request frequency, system computing power consumption, and current revenue price meet the balance conditions, including: If the historical request frequency is greater than the set value, and the system computing power consumption and the current revenue price satisfy the following formula (1), it is determined that the historical request frequency, system computing power consumption and the current revenue price meet the balance condition: a*c, where c is the system computing power consumption, a is the proportional coefficient, and Q is the current profit price; the proportional coefficient a is determined by the current system computing power C, the computing power consumption price coefficient q and the system computing power consumption. Specifically, the proportional coefficient a is obtained by the following formula (2): a=q*c / C (2); If the historical request frequency is less than or equal to the set value, and the system computing power consumption and the current revenue price do not satisfy formula (1), it is determined that the historical request frequency, the system computing power consumption and the current revenue price do not meet the balance condition. The system further comprises:

4. The system for generating a virtual traffic card according to claim 3, characterized in that: The flow card generation module is used to generate a virtual flow card if flow card confirmation information sent by the user is received, and the flow information of the virtual flow card is the flow card information. ​

Images